From 47b7aee14fd7e453370a5d15dfb11c958ca360f2 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 26 Sep 2018 16:12:06 +0100 Subject: [PATCH 01/23] sched/fair: Clean up load_balance() condition The alignment of the condition is off, clean that up. Also, logical operators have lower precedence than bitwise/relational operators, so remove one layer of parentheses to make the condition a bit simpler to follow. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar.Eggemann@arm.com Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: patrick.bellasi@arm.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1537974727-30788-1-git-send-email-valentin.schneider@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ee271bb661cc..4e298931a715 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8877,9 +8877,9 @@ out_all_pinned: out_one_pinned: /* tune up the balancing interval */ - if (((env.flags & LBF_ALL_PINNED) && - sd->balance_interval < MAX_PINNED_INTERVAL) || - (sd->balance_interval < sd->max_interval)) + if ((env.flags & LBF_ALL_PINNED && + sd->balance_interval < MAX_PINNED_INTERVAL) || + sd->balance_interval < sd->max_interval) sd->balance_interval *= 2; ld_moved = 0; From 3f130a37c442d5c4d66531b240ebe9abfef426b5 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 26 Sep 2018 16:12:07 +0100 Subject: [PATCH 02/23] sched/fair: Don't increase sd->balance_interval on newidle balance When load_balance() fails to move some load because of task affinity, we end up increasing sd->balance_interval to delay the next periodic balance in the hopes that next time we look, that annoying pinned task(s) will be gone. However, idle_balance() pays no attention to sd->balance_interval, yet it will still lead to an increase in balance_interval in case of pinned tasks. If we're going through several newidle balances (e.g. we have a periodic task), this can lead to a huge increase of the balance_interval in a very small amount of time. To prevent that, don't increase the balance interval when going through a newidle balance. This is a similar approach to what is done in commit 58b26c4c0257 ("sched: Increment cache_nice_tries only on periodic lb"), where we disregard newidle balance and rely on periodic balance for more stable results. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar.Eggemann@arm.com Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: patrick.bellasi@arm.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1537974727-30788-2-git-send-email-valentin.schneider@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4e298931a715..a17ca4254427 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8876,13 +8876,22 @@ out_all_pinned: sd->nr_balance_failed = 0; out_one_pinned: + ld_moved = 0; + + /* + * idle_balance() disregards balance intervals, so we could repeatedly + * reach this code, which would lead to balance_interval skyrocketting + * in a short amount of time. Skip the balance_interval increase logic + * to avoid that. + */ + if (env.idle == CPU_NEWLY_IDLE) + goto out; + /* tune up the balancing interval */ if ((env.flags & LBF_ALL_PINNED && sd->balance_interval < MAX_PINNED_INTERVAL) || sd->balance_interval < sd->max_interval) sd->balance_interval *= 2; - - ld_moved = 0; out: return ld_moved; } From ff1cdc94de4d336be45336d70709dfcf3d682514 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 26 Oct 2018 21:17:43 +0800 Subject: [PATCH 03/23] sched/core: Introduce set_next_task() helper for better code readability When we pick the next task, we will do the following for the task: 1) p->se.exec_start = rq_clock_task(rq); 2) dequeue_pushable(_dl)_task(rq, p); When we call set_curr_task(), we also need to do the same thing above. In rt.c, the code at 1) is in the _pick_next_task_rt() and the code at 2) is in the pick_next_task_rt(). If we put two operations in one function, maybe better. So, we introduce a new function set_next_task(), which is responsible for doing the above. By introducing the function we can get rid of calling the dequeue_pushable(_dl)_task() directly(We can call set_next_task()) in pick_next_task() and have better code readability and reuse. In set_curr_task_rt(), we also can call set_next_task(). Do this things such that we end up with: static struct task_struct *pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { /* do something else ... */ put_prev_task(rq, prev); /* pick next task p */ set_next_task(rq, p); /* do something else ... */ } put_prev_task() can match set_next_task(), which can make the code more readable. Signed-off-by: Muchun Song Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181026131743.21786-1-smuchun@gmail.com Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 19 ++++++++++--------- kernel/sched/rt.c | 24 +++++++++++------------- 2 files changed, 21 insertions(+), 22 deletions(-) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 91e4202b0634..470ba6b464fe 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1695,6 +1695,14 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p) } #endif +static inline void set_next_task(struct rq *rq, struct task_struct *p) +{ + p->se.exec_start = rq_clock_task(rq); + + /* You can't push away the running task */ + dequeue_pushable_dl_task(rq, p); +} + static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, struct dl_rq *dl_rq) { @@ -1750,10 +1758,8 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) BUG_ON(!dl_se); p = dl_task_of(dl_se); - p->se.exec_start = rq_clock_task(rq); - /* Running task will never be pushed. */ - dequeue_pushable_dl_task(rq, p); + set_next_task(rq, p); if (hrtick_enabled(rq)) start_hrtick_dl(rq, p); @@ -1808,12 +1814,7 @@ static void task_fork_dl(struct task_struct *p) static void set_curr_task_dl(struct rq *rq) { - struct task_struct *p = rq->curr; - - p->se.exec_start = rq_clock_task(rq); - - /* You can't push away the running task */ - dequeue_pushable_dl_task(rq, p); + set_next_task(rq, rq->curr); } #ifdef CONFIG_SMP diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a21ea6021929..9aa3287ce301 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1498,6 +1498,14 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag #endif } +static inline void set_next_task(struct rq *rq, struct task_struct *p) +{ + p->se.exec_start = rq_clock_task(rq); + + /* The running task is never eligible for pushing */ + dequeue_pushable_task(rq, p); +} + static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, struct rt_rq *rt_rq) { @@ -1518,7 +1526,6 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, static struct task_struct *_pick_next_task_rt(struct rq *rq) { struct sched_rt_entity *rt_se; - struct task_struct *p; struct rt_rq *rt_rq = &rq->rt; do { @@ -1527,10 +1534,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) rt_rq = group_rt_rq(rt_se); } while (rt_rq); - p = rt_task_of(rt_se); - p->se.exec_start = rq_clock_task(rq); - - return p; + return rt_task_of(rt_se); } static struct task_struct * @@ -1573,8 +1577,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) p = _pick_next_task_rt(rq); - /* The running task is never eligible for pushing */ - dequeue_pushable_task(rq, p); + set_next_task(rq, p); rt_queue_push_tasks(rq); @@ -2355,12 +2358,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) static void set_curr_task_rt(struct rq *rq) { - struct task_struct *p = rq->curr; - - p->se.exec_start = rq_clock_task(rq); - - /* The running task is never eligible for pushing */ - dequeue_pushable_task(rq, p); + set_next_task(rq, rq->curr); } static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) From 92a801e5d5b7a893881c1676b15dd246727ccd16 Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Mon, 5 Nov 2018 14:53:59 +0000 Subject: [PATCH 04/23] sched/fair: Mask UTIL_AVG_UNCHANGED usages The _task_util_est() is mainly used to add/remove the task contribution to/from the rq's estimated utilization at task enqueue/dequeue time. In both cases we ensure the UTIL_AVG_UNCHANGED flag is set to keep consistency between enqueue and dequeue time while still being transparent to update_load_avg calls which will eventually reset the flag. Let's move the flag forcing within _task_util_est() itself so that we can simplify calling code by hiding that estimated utilization implementation detail into one of its internal functions. This will affect also the "public" API task_util_est() but we know that the flag will (eventually) impact just on the LSB of the estimated utilization, thus it's certainly acceptable. Signed-off-by: Patrick Bellasi Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar Eggemann Cc: Juri Lelli Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Peter Zijlstra Cc: Quentin Perret Cc: Steve Muckle Cc: Suren Baghdasaryan Cc: Thomas Gleixner Cc: Todd Kjos Cc: Vincent Guittot Link: http://lkml.kernel.org/r/20181105145400.935-3-patrick.bellasi@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a1ccf1ddd37a..28ee60cabba1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3604,7 +3604,7 @@ static inline unsigned long _task_util_est(struct task_struct *p) { struct util_est ue = READ_ONCE(p->se.avg.util_est); - return max(ue.ewma, ue.enqueued); + return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED); } static inline unsigned long task_util_est(struct task_struct *p) @@ -3622,7 +3622,7 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq, /* Update root cfs_rq's estimated utilization */ enqueued = cfs_rq->avg.util_est.enqueued; - enqueued += (_task_util_est(p) | UTIL_AVG_UNCHANGED); + enqueued += _task_util_est(p); WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued); } @@ -3650,8 +3650,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) /* Update root cfs_rq's estimated utilization */ ue.enqueued = cfs_rq->avg.util_est.enqueued; - ue.enqueued -= min_t(unsigned int, ue.enqueued, - (_task_util_est(p) | UTIL_AVG_UNCHANGED)); + ue.enqueued -= min_t(unsigned int, ue.enqueued, _task_util_est(p)); WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued); /* @@ -6292,7 +6291,7 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p) */ if (unlikely(task_on_rq_queued(p) || current == p)) { estimated -= min_t(unsigned int, estimated, - (_task_util_est(p) | UTIL_AVG_UNCHANGED)); + _task_util_est(p)); } util = max(util, estimated); } From b5c0ce7bd1848892e2930f481828b6d7750231ed Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Mon, 5 Nov 2018 14:54:00 +0000 Subject: [PATCH 05/23] sched/fair: Add lsub_positive() and use it consistently The following pattern: var -= min_t(typeof(var), var, val); is used multiple times in fair.c. The existing sub_positive() already captures that pattern, but it also adds an explicit load-store to properly support lockless observations. In other cases the pattern above is used to update local, and/or not concurrently accessed, variables. Let's add a simpler version of sub_positive(), targeted at local variables updates, which gives the same readability benefits at calling sites, without enforcing {READ,WRITE}_ONCE() barriers. Signed-off-by: Patrick Bellasi Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar Eggemann Cc: Juri Lelli Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Peter Zijlstra Cc: Quentin Perret Cc: Steve Muckle Cc: Suren Baghdasaryan Cc: Thomas Gleixner Cc: Todd Kjos Cc: Vincent Guittot Link: https://lore.kernel.org/lkml/20181031184527.GA3178@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 28ee60cabba1..2cac9a469df4 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2734,6 +2734,17 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) WRITE_ONCE(*ptr, res); \ } while (0) +/* + * Remove and clamp on negative, from a local variable. + * + * A variant of sub_positive(), which does not use explicit load-store + * and is thus optimized for local variable updates. + */ +#define lsub_positive(_ptr, _val) do { \ + typeof(_ptr) ptr = (_ptr); \ + *ptr -= min_t(typeof(*ptr), *ptr, _val); \ +} while (0) + #ifdef CONFIG_SMP static inline void enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -4639,7 +4650,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) cfs_b->distribute_running = 0; throttled = !list_empty(&cfs_b->throttled_cfs_rq); - cfs_b->runtime -= min(runtime, cfs_b->runtime); + lsub_positive(&cfs_b->runtime, runtime); } /* @@ -4773,7 +4784,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) raw_spin_lock(&cfs_b->lock); if (expires == cfs_b->runtime_expires) - cfs_b->runtime -= min(runtime, cfs_b->runtime); + lsub_positive(&cfs_b->runtime, runtime); cfs_b->distribute_running = 0; raw_spin_unlock(&cfs_b->lock); } @@ -6240,7 +6251,7 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p) util = READ_ONCE(cfs_rq->avg.util_avg); /* Discount task's util from CPU's util */ - util -= min_t(unsigned int, util, task_util(p)); + lsub_positive(&util, task_util(p)); /* * Covered cases: @@ -6289,10 +6300,9 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p) * properly fix the execl regression and it helps in further * reducing the chances for the above race. */ - if (unlikely(task_on_rq_queued(p) || current == p)) { - estimated -= min_t(unsigned int, estimated, - _task_util_est(p)); - } + if (unlikely(task_on_rq_queued(p) || current == p)) + lsub_positive(&estimated, _task_util_est(p)); + util = max(util, estimated); } From 1da1843f9f0334e2428308945d396ffecc2acfe1 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 5 Nov 2018 16:51:55 +0530 Subject: [PATCH 06/23] sched/core: Create task_has_idle_policy() helper We already have task_has_rt_policy() and task_has_dl_policy() helpers, create task_has_idle_policy() as well and update sched core to start using it. While at it, use task_has_dl_policy() at one more place. Signed-off-by: Viresh Kumar Signed-off-by: Peter Zijlstra (Intel) Acked-by: Daniel Lezcano Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vincent Guittot Link: http://lkml.kernel.org/r/ce3915d5b490fc81af926a3b6bfb775e7188e005.1541416894.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 4 ++-- kernel/sched/debug.c | 2 +- kernel/sched/fair.c | 10 +++++----- kernel/sched/sched.h | 5 +++++ 4 files changed, 13 insertions(+), 8 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 02a20ef196a6..5afb868f7339 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -697,7 +697,7 @@ static void set_load_weight(struct task_struct *p, bool update_load) /* * SCHED_IDLE tasks get minimal weight: */ - if (idle_policy(p->policy)) { + if (task_has_idle_policy(p)) { load->weight = scale_load(WEIGHT_IDLEPRIO); load->inv_weight = WMULT_IDLEPRIO; p->se.runnable_weight = load->weight; @@ -4199,7 +4199,7 @@ recheck: * Treat SCHED_IDLE as nice 20. Only allow a switch to * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. */ - if (idle_policy(p->policy) && !idle_policy(policy)) { + if (task_has_idle_policy(p) && !idle_policy(policy)) { if (!can_nice(p, task_nice(p))) return -EPERM; } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 6383aa6a60ca..02bd5f969b21 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -974,7 +974,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, #endif P(policy); P(prio); - if (p->policy == SCHED_DEADLINE) { + if (task_has_dl_policy(p)) { P(dl.runtime); P(dl.deadline); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2cac9a469df4..d1f91e6efe51 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6529,7 +6529,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) static void set_last_buddy(struct sched_entity *se) { - if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se)))) return; for_each_sched_entity(se) { @@ -6541,7 +6541,7 @@ static void set_last_buddy(struct sched_entity *se) static void set_next_buddy(struct sched_entity *se) { - if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se)))) return; for_each_sched_entity(se) { @@ -6599,8 +6599,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; /* Idle tasks are by definition preempted by non-idle tasks. */ - if (unlikely(curr->policy == SCHED_IDLE) && - likely(p->policy != SCHED_IDLE)) + if (unlikely(task_has_idle_policy(curr)) && + likely(!task_has_idle_policy(p))) goto preempt; /* @@ -7021,7 +7021,7 @@ static int task_hot(struct task_struct *p, struct lb_env *env) if (p->sched_class != &fair_sched_class) return 0; - if (unlikely(p->policy == SCHED_IDLE)) + if (unlikely(task_has_idle_policy(p))) return 0; /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 618577fc9aa8..b7a3147874e3 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -176,6 +176,11 @@ static inline bool valid_policy(int policy) rt_policy(policy) || dl_policy(policy); } +static inline int task_has_idle_policy(struct task_struct *p) +{ + return idle_policy(p->policy); +} + static inline int task_has_rt_policy(struct task_struct *p) { return rt_policy(p->policy); From ed8885a14433aec04067463493051eaaeef3255f Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Sat, 10 Nov 2018 15:52:02 +0800 Subject: [PATCH 07/23] sched/fair: Make some variables static The variables are local to the source and do not need to be in global scope, so make them static. Signed-off-by: Muchun Song Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181110075202.61172-1-smuchun@gmail.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d1f91e6efe51..e30dea59d215 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -38,7 +38,7 @@ * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds) */ unsigned int sysctl_sched_latency = 6000000ULL; -unsigned int normalized_sysctl_sched_latency = 6000000ULL; +static unsigned int normalized_sysctl_sched_latency = 6000000ULL; /* * The initial- and re-scaling of tunables is configurable @@ -58,8 +58,8 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_L * * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds) */ -unsigned int sysctl_sched_min_granularity = 750000ULL; -unsigned int normalized_sysctl_sched_min_granularity = 750000ULL; +unsigned int sysctl_sched_min_granularity = 750000ULL; +static unsigned int normalized_sysctl_sched_min_granularity = 750000ULL; /* * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity @@ -81,8 +81,8 @@ unsigned int sysctl_sched_child_runs_first __read_mostly; * * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) */ -unsigned int sysctl_sched_wakeup_granularity = 1000000UL; -unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; +unsigned int sysctl_sched_wakeup_granularity = 1000000UL; +static unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; @@ -116,7 +116,7 @@ unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; * * (default: ~20%) */ -unsigned int capacity_margin = 1280; +static unsigned int capacity_margin = 1280; static inline void update_load_add(struct load_weight *lw, unsigned long inc) { From 3e184501083c38fa091f640acb13af17a21fd228 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Nov 2018 11:12:57 +0530 Subject: [PATCH 08/23] sched/core: Clean up the #ifdef block in add_nr_running() There is no point in keeping the conditional statement of the #if block outside of the #ifdef block, while all of its body is contained within the #ifdef block. Move the conditional statement under the #ifdef block as well. Signed-off-by: Viresh Kumar Cc: Daniel Lezcano Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vincent Guittot Link: http://lkml.kernel.org/r/78cbd78a615d6f9fdcd3327f1ead68470f92593e.1541482935.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b7a3147874e3..e0e052a50fcd 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1801,12 +1801,12 @@ static inline void add_nr_running(struct rq *rq, unsigned count) rq->nr_running = prev_nr + count; - if (prev_nr < 2 && rq->nr_running >= 2) { #ifdef CONFIG_SMP + if (prev_nr < 2 && rq->nr_running >= 2) { if (!READ_ONCE(rq->rd->overload)) WRITE_ONCE(rq->rd->overload, 1); -#endif } +#endif sched_update_tick_dependency(rq); } From dfcb245e28481256a10a9133441baf2a93d26642 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 3 Dec 2018 10:05:56 +0100 Subject: [PATCH 09/23] sched: Fix various typos in comments Go over the scheduler source code and fix common typos in comments - and a typo in an actual variable name. No change in functionality intended. Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Linus Torvalds Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- include/linux/sched/isolation.h | 4 ++-- include/linux/sched/mm.h | 2 +- include/linux/sched/stat.h | 2 +- kernel/sched/core.c | 2 +- kernel/sched/cputime.c | 2 +- kernel/sched/deadline.c | 2 +- kernel/sched/fair.c | 8 ++++---- kernel/sched/isolation.c | 14 +++++++------- kernel/sched/sched.h | 4 ++-- 10 files changed, 22 insertions(+), 22 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 291a9bd5b97f..b8c7ba0e3796 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -176,7 +176,7 @@ struct task_group; * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). * * However, with slightly different timing the wakeup TASK_RUNNING store can - * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not + * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not * a problem either because that will result in one extra go around the loop * and our @cond test will save the day. * @@ -515,7 +515,7 @@ struct sched_dl_entity { /* * Actual scheduling parameters. Initialized with the values above, - * they are continously updated during task execution. Note that + * they are continuously updated during task execution. Note that * the remaining runtime could be < 0 in case we are in overrun. */ s64 runtime; /* Remaining runtime for this instance */ diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 4a6582c27dea..b0fb1446fe04 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -16,7 +16,7 @@ enum hk_flags { }; #ifdef CONFIG_CPU_ISOLATION -DECLARE_STATIC_KEY_FALSE(housekeeping_overriden); +DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); extern int housekeeping_any_cpu(enum hk_flags flags); extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags); extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags); @@ -43,7 +43,7 @@ static inline void housekeeping_init(void) { } static inline bool housekeeping_cpu(int cpu, enum hk_flags flags) { #ifdef CONFIG_CPU_ISOLATION - if (static_branch_unlikely(&housekeeping_overriden)) + if (static_branch_unlikely(&housekeeping_overridden)) return housekeeping_test_cpu(cpu, flags); #endif return true; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index aebb370a0006..3bfa6a0cbba4 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -153,7 +153,7 @@ static inline gfp_t current_gfp_context(gfp_t flags) { /* * NOIO implies both NOIO and NOFS and it is a weaker context - * so always make sure it makes precendence + * so always make sure it makes precedence */ if (unlikely(current->flags & PF_MEMALLOC_NOIO)) flags &= ~(__GFP_IO | __GFP_FS); diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h index f30954cc059d..568286411b43 100644 --- a/include/linux/sched/stat.h +++ b/include/linux/sched/stat.h @@ -8,7 +8,7 @@ * Various counters maintained by the scheduler and fork(), * exposed via /proc, sys.c or used by drivers via these APIs. * - * ( Note that all these values are aquired without locking, + * ( Note that all these values are acquired without locking, * so they can only be relied on in narrow circumstances. ) */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8050f266751a..e4ca15d75541 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2857,7 +2857,7 @@ unsigned long nr_running(void) * preemption, thus the result might have a time-of-check-to-time-of-use * race. The caller is responsible to use it correctly, for example: * - * - from a non-preemptable section (of course) + * - from a non-preemptible section (of course) * * - from a thread that is bound to a single CPU * diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 0796f938c4f0..ba4a143bdcf3 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -525,7 +525,7 @@ void account_idle_ticks(unsigned long ticks) /* * Perform (stime * rtime) / total, but avoid multiplication overflow by - * loosing precision when the numbers are big. + * losing precision when the numbers are big. */ static u64 scale_stime(u64 stime, u64 rtime, u64 total) { diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 470ba6b464fe..b32bc1f7cd14 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -727,7 +727,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * refill the runtime and set the deadline a period in the future, * because keeping the current (absolute) deadline of the task would * result in breaking guarantees promised to other tasks (refer to - * Documentation/scheduler/sched-deadline.txt for more informations). + * Documentation/scheduler/sched-deadline.txt for more information). * * This function returns true if: * diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e30dea59d215..fdc8356ea742 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -703,9 +703,9 @@ void init_entity_runnable_average(struct sched_entity *se) memset(sa, 0, sizeof(*sa)); /* - * Tasks are intialized with full load to be seen as heavy tasks until + * Tasks are initialized with full load to be seen as heavy tasks until * they get a chance to stabilize to their real load level. - * Group entities are intialized with zero load to reflect the fact that + * Group entities are initialized with zero load to reflect the fact that * nothing has been attached to the task group yet. */ if (entity_is_task(se)) @@ -3976,8 +3976,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) /* * When dequeuing a sched_entity, we must: * - Update loads to have both entity and cfs_rq synced with now. - * - Substract its load from the cfs_rq->runnable_avg. - * - Substract its previous weight from cfs_rq->load.weight. + * - Subtract its load from the cfs_rq->runnable_avg. + * - Subtract its previous weight from cfs_rq->load.weight. * - For group entity, update its weight to reflect the new share * of its group cfs_rq. */ diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index e6802181900f..81faddba9e20 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -8,14 +8,14 @@ */ #include "sched.h" -DEFINE_STATIC_KEY_FALSE(housekeeping_overriden); -EXPORT_SYMBOL_GPL(housekeeping_overriden); +DEFINE_STATIC_KEY_FALSE(housekeeping_overridden); +EXPORT_SYMBOL_GPL(housekeeping_overridden); static cpumask_var_t housekeeping_mask; static unsigned int housekeeping_flags; int housekeeping_any_cpu(enum hk_flags flags) { - if (static_branch_unlikely(&housekeeping_overriden)) + if (static_branch_unlikely(&housekeeping_overridden)) if (housekeeping_flags & flags) return cpumask_any_and(housekeeping_mask, cpu_online_mask); return smp_processor_id(); @@ -24,7 +24,7 @@ EXPORT_SYMBOL_GPL(housekeeping_any_cpu); const struct cpumask *housekeeping_cpumask(enum hk_flags flags) { - if (static_branch_unlikely(&housekeeping_overriden)) + if (static_branch_unlikely(&housekeeping_overridden)) if (housekeeping_flags & flags) return housekeeping_mask; return cpu_possible_mask; @@ -33,7 +33,7 @@ EXPORT_SYMBOL_GPL(housekeeping_cpumask); void housekeeping_affine(struct task_struct *t, enum hk_flags flags) { - if (static_branch_unlikely(&housekeeping_overriden)) + if (static_branch_unlikely(&housekeeping_overridden)) if (housekeeping_flags & flags) set_cpus_allowed_ptr(t, housekeeping_mask); } @@ -41,7 +41,7 @@ EXPORT_SYMBOL_GPL(housekeeping_affine); bool housekeeping_test_cpu(int cpu, enum hk_flags flags) { - if (static_branch_unlikely(&housekeeping_overriden)) + if (static_branch_unlikely(&housekeeping_overridden)) if (housekeeping_flags & flags) return cpumask_test_cpu(cpu, housekeeping_mask); return true; @@ -53,7 +53,7 @@ void __init housekeeping_init(void) if (!housekeeping_flags) return; - static_branch_enable(&housekeeping_overriden); + static_branch_enable(&housekeeping_overridden); if (housekeeping_flags & HK_FLAG_TICK) sched_tick_offload_init(); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 71cd8b710599..9bde60a11805 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -637,7 +637,7 @@ struct dl_rq { /* * Deadline values of the currently executing and the * earliest ready task on this rq. Caching these facilitates - * the decision wether or not a ready but not running task + * the decision whether or not a ready but not running task * should migrate somewhere else. */ struct { @@ -1434,7 +1434,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) #ifdef CONFIG_SMP /* * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be - * successfuly executed on another CPU. We must ensure that updates of + * successfully executed on another CPU. We must ensure that updates of * per-task data have been completed by this moment. */ smp_wmb(); From 765d0af19f5f388a34bf4533378f8398b72ded46 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 29 Aug 2018 15:19:11 +0200 Subject: [PATCH 10/23] sched/topology: Remove the ::smt_gain field from 'struct sched_domain' ::smt_gain is used to compute the capacity of CPUs of a SMT core with the constraint 1 < ::smt_gain < 2 in order to be able to compute number of CPUs per core. The field has_free_capacity of struct numa_stat, which was the last user of this computation of number of CPUs per core, has been removed by: 2d4056fafa19 ("sched/numa: Remove numa_has_capacity()") We can now remove this constraint on core capacity and use the defautl value SCHED_CAPACITY_SCALE for SMT CPUs. With this remove, SCHED_CAPACITY_SCALE becomes the maximum compute capacity of CPUs on every systems. This should help to simplify some code and remove fields like rd->max_cpu_capacity Furthermore, arch_scale_cpu_capacity() is used with a NULL sd in several other places in the code when it wants the capacity of a CPUs to scale some metrics like in pelt, deadline or schedutil. In case on SMT, the value returned is not the capacity of SMT CPUs but default SCHED_CAPACITY_SCALE. So remove it. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1535548752-4434-4-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 1 - kernel/sched/sched.h | 3 --- kernel/sched/topology.c | 2 -- 3 files changed, 6 deletions(-) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 6b9976180c1e..7fa0bc17cd8c 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -89,7 +89,6 @@ struct sched_domain { unsigned int newidle_idx; unsigned int wake_idx; unsigned int forkexec_idx; - unsigned int smt_gain; int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 9bde60a11805..ceb896404869 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1864,9 +1864,6 @@ unsigned long arch_scale_freq_capacity(int cpu) static __always_inline unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) { - if (sd && (sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1)) - return sd->smt_gain / sd->span_weight; - return SCHED_CAPACITY_SCALE; } #endif diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 8d7f15ba5916..7364e0b427b7 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1133,7 +1133,6 @@ sd_init(struct sched_domain_topology_level *tl, .last_balance = jiffies, .balance_interval = sd_weight, - .smt_gain = 0, .max_newidle_lb_cost = 0, .next_decay_max_lb_cost = jiffies, .child = child, @@ -1164,7 +1163,6 @@ sd_init(struct sched_domain_topology_level *tl, if (sd->flags & SD_SHARE_CPUCAPACITY) { sd->imbalance_pct = 110; - sd->smt_gain = 1178; /* ~15% */ } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { sd->imbalance_pct = 117; From 9ebc6053814d37b9de8cc291fba28f30a729c929 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Sat, 3 Nov 2018 13:26:02 -0400 Subject: [PATCH 11/23] sched/core: Remove unnecessary unlikely() in push_*_task() WARN_ON() already contains an unlikely(), so it's not necessary to use WARN_ON(1). Signed-off-by: Yangtao Li Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181103172602.1917-1-tiny.windzz@gmail.com Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 4 +--- kernel/sched/rt.c | 4 +--- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index b32bc1f7cd14..fb8b7b5d745d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2042,10 +2042,8 @@ static int push_dl_task(struct rq *rq) return 0; retry: - if (unlikely(next_task == rq->curr)) { - WARN_ON(1); + if (WARN_ON(next_task == rq->curr)) return 0; - } /* * If next_task preempts rq->curr, and rq->curr diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 9aa3287ce301..e4f398ad9e73 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1813,10 +1813,8 @@ static int push_rt_task(struct rq *rq) return 0; retry: - if (unlikely(next_task == rq->curr)) { - WARN_ON(1); + if (WARN_ON(next_task == rq->curr)) return 0; - } /* * It's possible that the next_task slipped in of From 5bd0988be12733a42a1a3d50e3e2ddfd79e57518 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:14 +0000 Subject: [PATCH 12/23] sched/topology: Relocate arch_scale_cpu_capacity() to the internal header By default, arch_scale_cpu_capacity() is only visible from within the kernel/sched folder. Relocate it to include/linux/sched/topology.h to make it visible to other clients needing to know about the capacity of CPUs, such as the Energy Model framework. This also shrinks the public header. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-2-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 16 ++++++++++++++++ kernel/sched/sched.h | 18 ------------------ 2 files changed, 16 insertions(+), 18 deletions(-) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7fa0bc17cd8c..c31d3a47a47c 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -201,6 +201,14 @@ 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; @@ -216,6 +224,14 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu) return true; } +#ifndef arch_scale_cpu_capacity +static __always_inline +unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu) +{ + return SCHED_CAPACITY_SCALE; +} +#endif + #endif /* !CONFIG_SMP */ static inline int task_node(const struct task_struct *p) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index ceb896404869..66067152a831 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1859,24 +1859,6 @@ unsigned long arch_scale_freq_capacity(int cpu) } #endif -#ifdef CONFIG_SMP -#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 -#ifndef arch_scale_cpu_capacity -static __always_inline -unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu) -{ - return SCHED_CAPACITY_SCALE; -} -#endif -#endif - #ifdef CONFIG_SMP #ifdef CONFIG_PREEMPT From 938e5e4b0d1502a93e787985cb95b136b40717b7 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:15 +0000 Subject: [PATCH 13/23] sched/cpufreq: Prepare schedutil for Energy Aware Scheduling Schedutil requests frequency by aggregating utilization signals from the scheduler (CFS, RT, DL, IRQ) and applying a 25% margin on top of them. Since Energy Aware Scheduling (EAS) needs to be able to predict the frequency requests, it needs to forecast the decisions made by the governor. In order to prepare the introduction of EAS, introduce schedutil_freq_util() to centralize the aforementioned signal aggregation and make it available to both schedutil and EAS. Since frequency selection and energy estimation still need to deal with RT and DL signals slightly differently, schedutil_freq_util() is called with a different 'type' parameter in those two contexts, and returns an aggregated utilization signal accordingly. While at it, introduce the map_util_freq() function which is designed to make schedutil's 25% margin usable easily for both sugov and EAS. As EAS will be able to predict schedutil's frequency requests more accurately than any other governor by design, it'd be sensible to make sure EAS cannot be used without schedutil. This will be done later, once EAS has actually been introduced. Suggested-by: Peter Zijlstra Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-3-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched/cpufreq.h | 6 ++++ kernel/sched/cpufreq_schedutil.c | 53 +++++++++++++++++++++++--------- kernel/sched/sched.h | 30 ++++++++++++++++++ 3 files changed, 74 insertions(+), 15 deletions(-) diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index 59667444669f..afa940cd50dc 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -20,6 +20,12 @@ void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data, void (*func)(struct update_util_data *data, u64 time, unsigned int flags)); void cpufreq_remove_update_util_hook(int cpu); + +static inline unsigned long map_util_freq(unsigned long util, + unsigned long freq, unsigned long cap) +{ + return (freq + (freq >> 2)) * util / cap; +} #endif /* CONFIG_CPU_FREQ */ #endif /* _LINUX_SCHED_CPUFREQ_H */ diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 3fffad3bc8a8..90128be27712 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -13,6 +13,7 @@ #include "sched.h" +#include #include struct sugov_tunables { @@ -167,7 +168,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, unsigned int freq = arch_scale_freq_invariant() ? policy->cpuinfo.max_freq : policy->cur; - freq = (freq + (freq >> 2)) * util / max; + freq = map_util_freq(util, freq, max); if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update) return sg_policy->next_freq; @@ -197,15 +198,13 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, * based on the task model parameters and gives the minimal utilization * required to meet deadlines. */ -static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) +unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs, + unsigned long max, enum schedutil_type type) { - struct rq *rq = cpu_rq(sg_cpu->cpu); - unsigned long util, irq, max; + unsigned long dl_util, util, irq; + struct rq *rq = cpu_rq(cpu); - sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); - sg_cpu->bw_dl = cpu_bw_dl(rq); - - if (rt_rq_is_runnable(&rq->rt)) + if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) return max; /* @@ -223,21 +222,30 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) * utilization (PELT windows are synchronized) we can directly add them * to obtain the CPU's actual utilization. */ - util = cpu_util_cfs(rq); + util = util_cfs; util += cpu_util_rt(rq); + dl_util = cpu_util_dl(rq); + /* - * We do not make cpu_util_dl() a permanent part of this sum because we - * want to use cpu_bw_dl() later on, but we need to check if the - * CFS+RT+DL sum is saturated (ie. no idle time) such that we select - * f_max when there is no idle time. + * For frequency selection we do not make cpu_util_dl() a permanent part + * of this sum because we want to use cpu_bw_dl() later on, but we need + * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such + * that we select f_max when there is no idle time. * * NOTE: numerical errors or stop class might cause us to not quite hit * saturation when we should -- something for later. */ - if ((util + cpu_util_dl(rq)) >= max) + if (util + dl_util >= max) return max; + /* + * OTOH, for energy computation we need the estimated running time, so + * include util_dl and ignore dl_bw. + */ + if (type == ENERGY_UTIL) + util += dl_util; + /* * There is still idle time; further improve the number by using the * irq metric. Because IRQ/steal time is hidden from the task clock we @@ -260,7 +268,22 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) * bw_dl as requested freq. However, cpufreq is not yet ready for such * an interface. So, we only do the latter for now. */ - return min(max, util + sg_cpu->bw_dl); + if (type == FREQUENCY_UTIL) + util += cpu_bw_dl(rq); + + return min(max, util); +} + +static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) +{ + struct rq *rq = cpu_rq(sg_cpu->cpu); + unsigned long util = cpu_util_cfs(rq); + unsigned long max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); + + sg_cpu->max = max; + sg_cpu->bw_dl = cpu_bw_dl(rq); + + return schedutil_freq_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL); } /** diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 66067152a831..2eafa228aebf 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2191,6 +2191,31 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL +/** + * enum schedutil_type - CPU utilization type + * @FREQUENCY_UTIL: Utilization used to select frequency + * @ENERGY_UTIL: Utilization used during energy calculation + * + * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time + * need to be aggregated differently depending on the usage made of them. This + * enum is used within schedutil_freq_util() to differentiate the types of + * utilization expected by the callers, and adjust the aggregation accordingly. + */ +enum schedutil_type { + FREQUENCY_UTIL, + ENERGY_UTIL, +}; + +unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs, + unsigned long max, enum schedutil_type type); + +static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs) +{ + unsigned long max = arch_scale_cpu_capacity(NULL, cpu); + + return schedutil_freq_util(cpu, cfs, max, ENERGY_UTIL); +} + static inline unsigned long cpu_bw_dl(struct rq *rq) { return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT; @@ -2217,6 +2242,11 @@ static inline unsigned long cpu_util_rt(struct rq *rq) { return READ_ONCE(rq->avg_rt.util_avg); } +#else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */ +static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs) +{ + return cfs; +} #endif #ifdef CONFIG_HAVE_SCHED_AVG_IRQ From 27871f7a8a341ef5c636a337856369acf8013e4e Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:16 +0000 Subject: [PATCH 14/23] PM: Introduce an Energy Model management framework Several subsystems in the kernel (task scheduler and/or thermal at the time of writing) can benefit from knowing about the energy consumed by CPUs. Yet, this information can come from different sources (DT or firmware for example), in different formats, hence making it hard to exploit without a standard API. As an attempt to address this, introduce a centralized Energy Model (EM) management framework which aggregates the power values provided by drivers into a table for each performance domain in the system. The power cost tables are made available to interested clients (e.g. task scheduler or thermal) via platform-agnostic APIs. The overall design is represented by the diagram below (focused on Arm-related drivers as an example, but applicable to any architecture): +---------------+ +-----------------+ +-------------+ | Thermal (IPA) | | Scheduler (EAS) | | Other | +---------------+ +-----------------+ +-------------+ | | em_pd_energy() | | | em_cpu_get() | +-----------+ | +--------+ | | | v v v +---------------------+ | | | Energy Model | | | | Framework | | | +---------------------+ ^ ^ ^ | | | em_register_perf_domain() +----------+ | +---------+ | | | +---------------+ +---------------+ +--------------+ | cpufreq-dt | | arm_scmi | | Other | +---------------+ +---------------+ +--------------+ ^ ^ ^ | | | +--------------+ +---------------+ +--------------+ | Device Tree | | Firmware | | ? | +--------------+ +---------------+ +--------------+ Drivers (typically, but not limited to, CPUFreq drivers) can register data in the EM framework using the em_register_perf_domain() API. The calling driver must provide a callback function with a standardized signature that will be used by the EM framework to build the power cost tables of the performance domain. This design should offer a lot of flexibility to calling drivers which are free of reading information from any location and to use any technique to compute power costs. Moreover, the capacity states registered by drivers in the EM framework are not required to match real performance states of the target. This is particularly important on targets where the performance states are not known by the OS. The power cost coefficients managed by the EM framework are specified in milli-watts. Although the two potential users of those coefficients (IPA and EAS) only need relative correctness, IPA specifically needs to compare the power of CPUs with the power of other components (GPUs, for example), which are still expressed in absolute terms in their respective subsystems. Hence, specifying the power of CPUs in milli-watts should help transitioning IPA to using the EM framework without introducing new problems by keeping units comparable across sub-systems. On the longer term, the EM of other devices than CPUs could also be managed by the EM framework, which would enable to remove the absolute unit. However, this is not absolutely required as a first step, so this extension of the EM framework is left for later. On the client side, the EM framework offers APIs to access the power cost tables of a CPU (em_cpu_get()), and to estimate the energy consumed by the CPUs of a performance domain (em_pd_energy()). Clients such as the task scheduler can then use these APIs to access the shared data structures holding the Energy Model of CPUs. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-4-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- include/linux/energy_model.h | 187 ++++++++++++++++++++++++++++++++ kernel/power/Kconfig | 15 +++ kernel/power/Makefile | 2 + kernel/power/energy_model.c | 201 +++++++++++++++++++++++++++++++++++ 4 files changed, 405 insertions(+) create mode 100644 include/linux/energy_model.h create mode 100644 kernel/power/energy_model.c diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h new file mode 100644 index 000000000000..aa027f7bcb3e --- /dev/null +++ b/include/linux/energy_model.h @@ -0,0 +1,187 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ENERGY_MODEL_H +#define _LINUX_ENERGY_MODEL_H +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_ENERGY_MODEL +/** + * em_cap_state - Capacity state of a performance domain + * @frequency: The CPU frequency in KHz, for consistency with CPUFreq + * @power: The power consumed by 1 CPU at this level, in milli-watts + * @cost: The cost coefficient associated with this level, used during + * energy calculation. Equal to: power * max_frequency / frequency + */ +struct em_cap_state { + unsigned long frequency; + unsigned long power; + unsigned long cost; +}; + +/** + * em_perf_domain - Performance domain + * @table: List of capacity states, in ascending order + * @nr_cap_states: Number of capacity states + * @cpus: Cpumask covering the CPUs of the domain + * + * A "performance domain" represents a group of CPUs whose performance is + * scaled together. All CPUs of a performance domain must have the same + * micro-architecture. Performance domains often have a 1-to-1 mapping with + * CPUFreq policies. + */ +struct em_perf_domain { + struct em_cap_state *table; + int nr_cap_states; + unsigned long cpus[0]; +}; + +#define EM_CPU_MAX_POWER 0xFFFF + +struct em_data_callback { + /** + * active_power() - Provide power at the next capacity state of a CPU + * @power : Active power at the capacity state in mW (modified) + * @freq : Frequency at the capacity state in kHz (modified) + * @cpu : CPU for which we do this operation + * + * active_power() must find the lowest capacity state of 'cpu' above + * 'freq' and update 'power' and 'freq' to the matching active power + * and frequency. + * + * The power is the one of a single CPU in the domain, expressed in + * milli-watts. It is expected to fit in the [0, EM_CPU_MAX_POWER] + * range. + * + * Return 0 on success. + */ + int (*active_power)(unsigned long *power, unsigned long *freq, int cpu); +}; +#define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } + +struct em_perf_domain *em_cpu_get(int cpu); +int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, + struct em_data_callback *cb); + +/** + * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain + * @pd : performance domain for which energy has to be estimated + * @max_util : highest utilization among CPUs of the domain + * @sum_util : sum of the utilization of all CPUs in the domain + * + * Return: the sum of the energy consumed by the CPUs of the domain assuming + * a capacity state satisfying the max utilization of the domain. + */ +static inline unsigned long em_pd_energy(struct em_perf_domain *pd, + unsigned long max_util, unsigned long sum_util) +{ + unsigned long freq, scale_cpu; + struct em_cap_state *cs; + int i, cpu; + + /* + * In order to predict the capacity state, map the utilization of the + * most utilized CPU of the performance domain to a requested frequency, + * like schedutil. + */ + cpu = cpumask_first(to_cpumask(pd->cpus)); + scale_cpu = arch_scale_cpu_capacity(NULL, cpu); + cs = &pd->table[pd->nr_cap_states - 1]; + freq = map_util_freq(max_util, cs->frequency, scale_cpu); + + /* + * Find the lowest capacity state of the Energy Model above the + * requested frequency. + */ + for (i = 0; i < pd->nr_cap_states; i++) { + cs = &pd->table[i]; + if (cs->frequency >= freq) + break; + } + + /* + * The capacity of a CPU in the domain at that capacity state (cs) + * can be computed as: + * + * cs->freq * scale_cpu + * cs->cap = -------------------- (1) + * cpu_max_freq + * + * So, ignoring the costs of idle states (which are not available in + * the EM), the energy consumed by this CPU at that capacity state is + * estimated as: + * + * cs->power * cpu_util + * cpu_nrg = -------------------- (2) + * cs->cap + * + * since 'cpu_util / cs->cap' represents its percentage of busy time. + * + * NOTE: Although the result of this computation actually is in + * units of power, it can be manipulated as an energy value + * over a scheduling period, since it is assumed to be + * constant during that interval. + * + * By injecting (1) in (2), 'cpu_nrg' can be re-expressed as a product + * of two terms: + * + * cs->power * cpu_max_freq cpu_util + * cpu_nrg = ------------------------ * --------- (3) + * cs->freq scale_cpu + * + * The first term is static, and is stored in the em_cap_state struct + * as 'cs->cost'. + * + * Since all CPUs of the domain have the same micro-architecture, they + * share the same 'cs->cost', and the same CPU capacity. Hence, the + * total energy of the domain (which is the simple sum of the energy of + * all of its CPUs) can be factorized as: + * + * cs->cost * \Sum cpu_util + * pd_nrg = ------------------------ (4) + * scale_cpu + */ + return cs->cost * sum_util / scale_cpu; +} + +/** + * em_pd_nr_cap_states() - Get the number of capacity states of a perf. domain + * @pd : performance domain for which this must be done + * + * Return: the number of capacity states in the performance domain table + */ +static inline int em_pd_nr_cap_states(struct em_perf_domain *pd) +{ + return pd->nr_cap_states; +} + +#else +struct em_perf_domain {}; +struct em_data_callback {}; +#define EM_DATA_CB(_active_power_cb) { } + +static inline int em_register_perf_domain(cpumask_t *span, + unsigned int nr_states, struct em_data_callback *cb) +{ + return -EINVAL; +} +static inline struct em_perf_domain *em_cpu_get(int cpu) +{ + return NULL; +} +static inline unsigned long em_pd_energy(struct em_perf_domain *pd, + unsigned long max_util, unsigned long sum_util) +{ + return 0; +} +static inline int em_pd_nr_cap_states(struct em_perf_domain *pd) +{ + return 0; +} +#endif + +#endif diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 3a6c2f87699e..f8fe57d1022e 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -298,3 +298,18 @@ config PM_GENERIC_DOMAINS_OF config CPU_PM bool + +config ENERGY_MODEL + bool "Energy Model for CPUs" + depends on SMP + depends on CPU_FREQ + default n + help + Several subsystems (thermal and/or the task scheduler for example) + can leverage information about the energy consumed by CPUs to make + smarter decisions. This config option enables the framework from + which subsystems can access the energy models. + + The exact usage of the energy model is subsystem-dependent. + + If in doubt, say N. diff --git a/kernel/power/Makefile b/kernel/power/Makefile index a3f79f0eef36..e7e47d9be1e5 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -15,3 +15,5 @@ obj-$(CONFIG_PM_AUTOSLEEP) += autosleep.o obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o + +obj-$(CONFIG_ENERGY_MODEL) += energy_model.o diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c new file mode 100644 index 000000000000..d9dc2c38764a --- /dev/null +++ b/kernel/power/energy_model.c @@ -0,0 +1,201 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Energy Model of CPUs + * + * Copyright (c) 2018, Arm ltd. + * Written by: Quentin Perret, Arm ltd. + */ + +#define pr_fmt(fmt) "energy_model: " fmt + +#include +#include +#include +#include +#include + +/* Mapping of each CPU to the performance domain to which it belongs. */ +static DEFINE_PER_CPU(struct em_perf_domain *, em_data); + +/* + * Mutex serializing the registrations of performance domains and letting + * callbacks defined by drivers sleep. + */ +static DEFINE_MUTEX(em_pd_mutex); + +static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states, + struct em_data_callback *cb) +{ + unsigned long opp_eff, prev_opp_eff = ULONG_MAX; + unsigned long power, freq, prev_freq = 0; + int i, ret, cpu = cpumask_first(span); + struct em_cap_state *table; + struct em_perf_domain *pd; + u64 fmax; + + if (!cb->active_power) + return NULL; + + pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL); + if (!pd) + return NULL; + + table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL); + if (!table) + goto free_pd; + + /* Build the list of capacity states for this performance domain */ + for (i = 0, freq = 0; i < nr_states; i++, freq++) { + /* + * active_power() is a driver callback which ceils 'freq' to + * lowest capacity state of 'cpu' above 'freq' and updates + * 'power' and 'freq' accordingly. + */ + ret = cb->active_power(&power, &freq, cpu); + if (ret) { + pr_err("pd%d: invalid cap. state: %d\n", cpu, ret); + goto free_cs_table; + } + + /* + * We expect the driver callback to increase the frequency for + * higher capacity states. + */ + if (freq <= prev_freq) { + pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq); + goto free_cs_table; + } + + /* + * The power returned by active_state() is expected to be + * positive, in milli-watts and to fit into 16 bits. + */ + if (!power || power > EM_CPU_MAX_POWER) { + pr_err("pd%d: invalid power: %lu\n", cpu, power); + goto free_cs_table; + } + + table[i].power = power; + table[i].frequency = prev_freq = freq; + + /* + * The hertz/watts efficiency ratio should decrease as the + * frequency grows on sane platforms. But this isn't always + * true in practice so warn the user if a higher OPP is more + * power efficient than a lower one. + */ + opp_eff = freq / power; + if (opp_eff >= prev_opp_eff) + pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_cap_state %d >= em_cap_state%d\n", + cpu, i, i - 1); + prev_opp_eff = opp_eff; + } + + /* Compute the cost of each capacity_state. */ + fmax = (u64) table[nr_states - 1].frequency; + for (i = 0; i < nr_states; i++) { + table[i].cost = div64_u64(fmax * table[i].power, + table[i].frequency); + } + + pd->table = table; + pd->nr_cap_states = nr_states; + cpumask_copy(to_cpumask(pd->cpus), span); + + return pd; + +free_cs_table: + kfree(table); +free_pd: + kfree(pd); + + return NULL; +} + +/** + * em_cpu_get() - Return the performance domain for a CPU + * @cpu : CPU to find the performance domain for + * + * Return: the performance domain to which 'cpu' belongs, or NULL if it doesn't + * exist. + */ +struct em_perf_domain *em_cpu_get(int cpu) +{ + return READ_ONCE(per_cpu(em_data, cpu)); +} +EXPORT_SYMBOL_GPL(em_cpu_get); + +/** + * em_register_perf_domain() - Register the Energy Model of a performance domain + * @span : Mask of CPUs in the performance domain + * @nr_states : Number of capacity states to register + * @cb : Callback functions providing the data of the Energy Model + * + * Create Energy Model tables for a performance domain using the callbacks + * defined in cb. + * + * If multiple clients register the same performance domain, all but the first + * registration will be ignored. + * + * Return 0 on success + */ +int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, + struct em_data_callback *cb) +{ + unsigned long cap, prev_cap = 0; + struct em_perf_domain *pd; + int cpu, ret = 0; + + if (!span || !nr_states || !cb) + return -EINVAL; + + /* + * Use a mutex to serialize the registration of performance domains and + * let the driver-defined callback functions sleep. + */ + mutex_lock(&em_pd_mutex); + + for_each_cpu(cpu, span) { + /* Make sure we don't register again an existing domain. */ + if (READ_ONCE(per_cpu(em_data, cpu))) { + ret = -EEXIST; + goto unlock; + } + + /* + * All CPUs of a domain must have the same micro-architecture + * since they all share the same table. + */ + cap = arch_scale_cpu_capacity(NULL, cpu); + if (prev_cap && prev_cap != cap) { + pr_err("CPUs of %*pbl must have the same capacity\n", + cpumask_pr_args(span)); + ret = -EINVAL; + goto unlock; + } + prev_cap = cap; + } + + /* Create the performance domain and add it to the Energy Model. */ + pd = em_create_pd(span, nr_states, cb); + if (!pd) { + ret = -EINVAL; + goto unlock; + } + + for_each_cpu(cpu, span) { + /* + * The per-cpu array can be read concurrently from em_cpu_get(). + * The barrier enforces the ordering needed to make sure readers + * can only access well formed em_perf_domain structs. + */ + smp_store_release(per_cpu_ptr(&em_data, cpu), pd); + } + + pr_debug("Created perf domain %*pbl\n", cpumask_pr_args(span)); +unlock: + mutex_unlock(&em_pd_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(em_register_perf_domain); From 6aa140fa4508933a6ac6717d65a403eb904d6c02 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:18 +0000 Subject: [PATCH 15/23] sched/topology: Reference the Energy Model of CPUs when available The existing scheduling domain hierarchy is defined to map to the cache topology of the system. However, Energy Aware Scheduling (EAS) requires more knowledge about the platform, and specifically needs to know about the span of Performance Domains (PD), which do not always align with caches. To address this issue, use the Energy Model (EM) of the system to extend the scheduler topology code with a representation of the PDs, alongside the scheduling domains. More specifically, a linked list of PDs is attached to each root domain. When multiple root domains are in use, each list contains only the PDs covering the CPUs of its root domain. If a PD spans over CPUs of multiple different root domains, it will be duplicated in all lists. The lists are fully maintained by the scheduler from partition_sched_domains() in order to cope with hotplug and cpuset changes. As for scheduling domains, the list are protected by RCU to ensure safe concurrent updates. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-6-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/sched.h | 21 +++++++ kernel/sched/topology.c | 134 ++++++++++++++++++++++++++++++++++++++-- 2 files changed, 151 insertions(+), 4 deletions(-) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 2eafa228aebf..808a565187b1 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -45,6 +45,7 @@ #include #include #include +#include #include #include #include @@ -709,6 +710,12 @@ static inline bool sched_asym_prefer(int a, int b) return arch_asym_cpu_priority(a) > arch_asym_cpu_priority(b); } +struct perf_domain { + struct em_perf_domain *em_pd; + struct perf_domain *next; + struct rcu_head rcu; +}; + /* * We add the notion of a root-domain which will be used to define per-domain * variables. Each exclusive cpuset essentially defines an island domain by @@ -761,6 +768,12 @@ struct root_domain { struct cpupri cpupri; unsigned long max_cpu_capacity; + + /* + * NULL-terminated list of performance domains intersecting with the + * CPUs of the rd. Protected by RCU. + */ + struct perf_domain *pd; }; extern struct root_domain def_root_domain; @@ -2276,3 +2289,11 @@ unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned return util; } #endif + +#ifdef CONFIG_SMP +#ifdef CONFIG_ENERGY_MODEL +#define perf_domain_span(pd) (to_cpumask(((pd)->em_pd->cpus))) +#else +#define perf_domain_span(pd) NULL +#endif +#endif diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 7364e0b427b7..169d25cafab5 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -201,6 +201,116 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) return 1; } +#ifdef CONFIG_ENERGY_MODEL +static void free_pd(struct perf_domain *pd) +{ + struct perf_domain *tmp; + + while (pd) { + tmp = pd->next; + kfree(pd); + pd = tmp; + } +} + +static struct perf_domain *find_pd(struct perf_domain *pd, int cpu) +{ + while (pd) { + if (cpumask_test_cpu(cpu, perf_domain_span(pd))) + return pd; + pd = pd->next; + } + + return NULL; +} + +static struct perf_domain *pd_init(int cpu) +{ + struct em_perf_domain *obj = em_cpu_get(cpu); + struct perf_domain *pd; + + if (!obj) { + if (sched_debug()) + pr_info("%s: no EM found for CPU%d\n", __func__, cpu); + return NULL; + } + + pd = kzalloc(sizeof(*pd), GFP_KERNEL); + if (!pd) + return NULL; + pd->em_pd = obj; + + return pd; +} + +static void perf_domain_debug(const struct cpumask *cpu_map, + struct perf_domain *pd) +{ + if (!sched_debug() || !pd) + return; + + printk(KERN_DEBUG "root_domain %*pbl:", cpumask_pr_args(cpu_map)); + + while (pd) { + printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_cstate=%d }", + cpumask_first(perf_domain_span(pd)), + cpumask_pr_args(perf_domain_span(pd)), + em_pd_nr_cap_states(pd->em_pd)); + pd = pd->next; + } + + printk(KERN_CONT "\n"); +} + +static void destroy_perf_domain_rcu(struct rcu_head *rp) +{ + struct perf_domain *pd; + + pd = container_of(rp, struct perf_domain, rcu); + free_pd(pd); +} + +static void build_perf_domains(const struct cpumask *cpu_map) +{ + struct perf_domain *pd = NULL, *tmp; + int cpu = cpumask_first(cpu_map); + struct root_domain *rd = cpu_rq(cpu)->rd; + int i; + + for_each_cpu(i, cpu_map) { + /* Skip already covered CPUs. */ + if (find_pd(pd, i)) + continue; + + /* Create the new pd and add it to the local list. */ + tmp = pd_init(i); + if (!tmp) + goto free; + tmp->next = pd; + pd = tmp; + } + + perf_domain_debug(cpu_map, pd); + + /* Attach the new list of performance domains to the root domain. */ + tmp = rd->pd; + rcu_assign_pointer(rd->pd, pd); + if (tmp) + call_rcu(&tmp->rcu, destroy_perf_domain_rcu); + + return; + +free: + free_pd(pd); + tmp = rd->pd; + rcu_assign_pointer(rd->pd, NULL); + if (tmp) + call_rcu(&tmp->rcu, destroy_perf_domain_rcu); +} +#else +static void free_pd(struct perf_domain *pd) { } +#endif /* CONFIG_ENERGY_MODEL */ + static void free_rootdomain(struct rcu_head *rcu) { struct root_domain *rd = container_of(rcu, struct root_domain, rcu); @@ -211,6 +321,7 @@ static void free_rootdomain(struct rcu_head *rcu) free_cpumask_var(rd->rto_mask); free_cpumask_var(rd->online); free_cpumask_var(rd->span); + free_pd(rd->pd); kfree(rd); } @@ -1959,8 +2070,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], /* Destroy deleted domains: */ for (i = 0; i < ndoms_cur; i++) { for (j = 0; j < n && !new_topology; j++) { - if (cpumask_equal(doms_cur[i], doms_new[j]) - && dattrs_equal(dattr_cur, i, dattr_new, j)) + if (cpumask_equal(doms_cur[i], doms_new[j]) && + dattrs_equal(dattr_cur, i, dattr_new, j)) goto match1; } /* No match - a current sched domain not in new doms_new[] */ @@ -1980,8 +2091,8 @@ match1: /* Build new domains: */ for (i = 0; i < ndoms_new; i++) { for (j = 0; j < n && !new_topology; j++) { - if (cpumask_equal(doms_new[i], doms_cur[j]) - && dattrs_equal(dattr_new, i, dattr_cur, j)) + if (cpumask_equal(doms_new[i], doms_cur[j]) && + dattrs_equal(dattr_new, i, dattr_cur, j)) goto match2; } /* No match - add a new doms_new */ @@ -1990,6 +2101,21 @@ match2: ; } +#ifdef CONFIG_ENERGY_MODEL + /* Build perf. domains: */ + for (i = 0; i < ndoms_new; i++) { + for (j = 0; j < n; j++) { + if (cpumask_equal(doms_new[i], doms_cur[j]) && + cpu_rq(cpumask_first(doms_cur[j]))->rd->pd) + goto match3; + } + /* No match - add perf. domains for a new rd */ + build_perf_domains(doms_new[i]); +match3: + ; + } +#endif + /* Remember the new sched domains: */ if (doms_cur != &fallback_doms) free_sched_domains(doms_cur, ndoms_cur); From 011b27bb5d3139e8b5fe9ceff1fc7f6dc3145071 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:19 +0000 Subject: [PATCH 16/23] sched/topology: Add lowest CPU asymmetry sched_domain level pointer Add another member to the family of per-cpu sched_domain shortcut pointers. This one, sd_asym_cpucapacity, points to the lowest level at which the SD_ASYM_CPUCAPACITY flag is set. While at it, rename the sd_asym shortcut to sd_asym_packing to avoid confusions. Generally speaking, the largest opportunity to save energy via scheduling comes from a smarter exploitation of heterogeneous platforms (i.e. big.LITTLE). Consequently, the sd_asym_cpucapacity shortcut will be used at first as the lowest domain where Energy-Aware Scheduling (EAS) should be applied. For example, it is possible to apply EAS within a socket on a multi-socket system, as long as each socket has an asymmetric topology. Energy-aware cross-sockets wake-up balancing will only happen when the system is over-utilized, or this_cpu and prev_cpu are in different sockets. Suggested-by: Morten Rasmussen Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-7-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 2 +- kernel/sched/sched.h | 3 ++- kernel/sched/topology.c | 8 ++++++-- 3 files changed, 9 insertions(+), 4 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index fdc8356ea742..a31a6d325901 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9299,7 +9299,7 @@ static void nohz_balancer_kick(struct rq *rq) } } - sd = rcu_dereference(per_cpu(sd_asym, cpu)); + sd = rcu_dereference(per_cpu(sd_asym_packing, cpu)); if (sd) { for_each_cpu(i, sched_domain_span(sd)) { if (i == cpu || diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 808a565187b1..75c403674706 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1303,7 +1303,8 @@ DECLARE_PER_CPU(int, sd_llc_size); DECLARE_PER_CPU(int, sd_llc_id); DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); DECLARE_PER_CPU(struct sched_domain *, sd_numa); -DECLARE_PER_CPU(struct sched_domain *, sd_asym); +DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing); +DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity); extern struct static_key_false sched_asym_cpucapacity; struct sched_group_capacity { diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 169d25cafab5..137ccfed9a43 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -508,7 +508,8 @@ DEFINE_PER_CPU(int, sd_llc_size); DEFINE_PER_CPU(int, sd_llc_id); DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); DEFINE_PER_CPU(struct sched_domain *, sd_numa); -DEFINE_PER_CPU(struct sched_domain *, sd_asym); +DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing); +DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity); DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity); static void update_top_cache_domain(int cpu) @@ -534,7 +535,10 @@ static void update_top_cache_domain(int cpu) rcu_assign_pointer(per_cpu(sd_numa, cpu), sd); sd = highest_flag_domain(cpu, SD_ASYM_PACKING); - rcu_assign_pointer(per_cpu(sd_asym, cpu), sd); + rcu_assign_pointer(per_cpu(sd_asym_packing, cpu), sd); + + sd = lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY); + rcu_assign_pointer(per_cpu(sd_asym_cpucapacity, cpu), sd); } /* From b68a4c0dba3b1e1dda1ede49f3c2fc72d3b54567 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:20 +0000 Subject: [PATCH 17/23] sched/topology: Disable EAS on inappropriate platforms Energy Aware Scheduling (EAS) in its current form is most relevant on platforms with asymmetric CPU topologies (e.g. Arm big.LITTLE) since this is where there is a lot of potential for saving energy through scheduling. This is particularly true since the Energy Model only includes the active power costs of CPUs, hence not providing enough data to compare packing-vs-spreading strategies. As such, disable EAS on root domains where the SD_ASYM_CPUCAPACITY flag is not set. While at it, disable EAS on systems where the complexity of the Energy Model is too high since that could lead to unacceptable scheduling overhead. All in all, EAS can be used on a root domain if and only if: 1. an Energy Model is available; 2. the root domain has an asymmetric CPU capacity topology; 3. the complexity of the root domain's EM is low enough to keep scheduling overheads low. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-8-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/topology.c | 49 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 48 insertions(+), 1 deletion(-) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 137ccfed9a43..6ddb804b2dec 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -270,12 +270,45 @@ static void destroy_perf_domain_rcu(struct rcu_head *rp) free_pd(pd); } +/* + * EAS can be used on a root domain if it meets all the following conditions: + * 1. an Energy Model (EM) is available; + * 2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy. + * 3. the EM complexity is low enough to keep scheduling overheads low; + * + * The complexity of the Energy Model is defined as: + * + * C = nr_pd * (nr_cpus + nr_cs) + * + * with parameters defined as: + * - nr_pd: the number of performance domains + * - nr_cpus: the number of CPUs + * - nr_cs: the sum of the number of capacity states of all performance + * domains (for example, on a system with 2 performance domains, + * with 10 capacity states each, nr_cs = 2 * 10 = 20). + * + * It is generally not a good idea to use such a model in the wake-up path on + * very complex platforms because of the associated scheduling overheads. The + * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs + * with per-CPU DVFS and less than 8 capacity states each, for example. + */ +#define EM_MAX_COMPLEXITY 2048 + static void build_perf_domains(const struct cpumask *cpu_map) { + int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map); struct perf_domain *pd = NULL, *tmp; int cpu = cpumask_first(cpu_map); struct root_domain *rd = cpu_rq(cpu)->rd; - int i; + + /* EAS is enabled for asymmetric CPU capacity topologies. */ + if (!per_cpu(sd_asym_cpucapacity, cpu)) { + if (sched_debug()) { + pr_info("rd %*pbl: CPUs do not have asymmetric capacities\n", + cpumask_pr_args(cpu_map)); + } + goto free; + } for_each_cpu(i, cpu_map) { /* Skip already covered CPUs. */ @@ -288,6 +321,20 @@ static void build_perf_domains(const struct cpumask *cpu_map) goto free; tmp->next = pd; pd = tmp; + + /* + * Count performance domains and capacity states for the + * complexity check. + */ + nr_pd++; + nr_cs += em_pd_nr_cap_states(pd->em_pd); + } + + /* Bail out if the Energy Model complexity is too high. */ + if (nr_pd * (nr_cs + nr_cpus) > EM_MAX_COMPLEXITY) { + WARN(1, "rd %*pbl: Failed to start EAS, EM complexity is too high\n", + cpumask_pr_args(cpu_map)); + goto free; } perf_domain_debug(cpu_map, pd); From 531b5c9f5cd05ead53324f419b32685a22eebe8b Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:21 +0000 Subject: [PATCH 18/23] sched/topology: Make Energy Aware Scheduling depend on schedutil Energy Aware Scheduling (EAS) is designed with the assumption that frequencies of CPUs follow their utilization value. When using a CPUFreq governor other than schedutil, the chances of this assumption being true are small, if any. When schedutil is being used, EAS' predictions are at least consistent with the frequency requests. Although those requests have no guarantees to be honored by the hardware, they should at least guide DVFS in the right direction and provide some hope in regards to the EAS model being accurate. To make sure EAS is only used in a sane configuration, create a strong dependency on schedutil being used. Since having sugov compiled-in does not provide that guarantee, make CPUFreq call a scheduler function on governor changes hence letting it rebuild the scheduling domains, check the governors of the online CPUs, and enable/disable EAS accordingly. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-9-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- drivers/cpufreq/cpufreq.c | 1 + include/linux/cpufreq.h | 8 +++++++ kernel/sched/cpufreq_schedutil.c | 37 ++++++++++++++++++++++++++++++-- kernel/sched/sched.h | 4 +--- kernel/sched/topology.c | 28 ++++++++++++++++++++---- 5 files changed, 69 insertions(+), 9 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 7aa3dcad2175..6f23ebb395f1 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2277,6 +2277,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, ret = cpufreq_start_governor(policy); if (!ret) { pr_debug("cpufreq: governor change\n"); + sched_cpufreq_governor_change(policy, old_gov); return 0; } cpufreq_exit_governor(policy); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 882a9b9e34bc..c86d6d8bdfed 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -950,6 +950,14 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) } #endif +#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) +void sched_cpufreq_governor_change(struct cpufreq_policy *policy, + struct cpufreq_governor *old_gov); +#else +static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, + struct cpufreq_governor *old_gov) { } +#endif + extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 90128be27712..c2e53d1a3143 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -624,7 +624,7 @@ static struct kobj_type sugov_tunables_ktype = { /********************** cpufreq governor interface *********************/ -static struct cpufreq_governor schedutil_gov; +struct cpufreq_governor schedutil_gov; static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy) { @@ -883,7 +883,7 @@ static void sugov_limits(struct cpufreq_policy *policy) sg_policy->need_freq_update = true; } -static struct cpufreq_governor schedutil_gov = { +struct cpufreq_governor schedutil_gov = { .name = "schedutil", .owner = THIS_MODULE, .dynamic_switching = true, @@ -906,3 +906,36 @@ static int __init sugov_register(void) return cpufreq_register_governor(&schedutil_gov); } fs_initcall(sugov_register); + +#ifdef CONFIG_ENERGY_MODEL +extern bool sched_energy_update; +extern struct mutex sched_energy_mutex; + +static void rebuild_sd_workfn(struct work_struct *work) +{ + mutex_lock(&sched_energy_mutex); + sched_energy_update = true; + rebuild_sched_domains(); + sched_energy_update = false; + mutex_unlock(&sched_energy_mutex); +} +static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn); + +/* + * EAS shouldn't be attempted without sugov, so rebuild the sched_domains + * on governor changes to make sure the scheduler knows about it. + */ +void sched_cpufreq_governor_change(struct cpufreq_policy *policy, + struct cpufreq_governor *old_gov) +{ + if (old_gov == &schedutil_gov || policy->governor == &schedutil_gov) { + /* + * When called from the cpufreq_register_driver() path, the + * cpu_hotplug_lock is already held, so use a work item to + * avoid nested locking in rebuild_sched_domains(). + */ + schedule_work(&rebuild_sd_work); + } + +} +#endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 75c403674706..fd84900b0b21 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2291,10 +2291,8 @@ unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned } #endif -#ifdef CONFIG_SMP -#ifdef CONFIG_ENERGY_MODEL +#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) #define perf_domain_span(pd) (to_cpumask(((pd)->em_pd->cpus))) #else #define perf_domain_span(pd) NULL #endif -#endif diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 6ddb804b2dec..0a5a1d3a4eae 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -201,7 +201,10 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) return 1; } -#ifdef CONFIG_ENERGY_MODEL +#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) +DEFINE_MUTEX(sched_energy_mutex); +bool sched_energy_update; + static void free_pd(struct perf_domain *pd) { struct perf_domain *tmp; @@ -275,6 +278,7 @@ static void destroy_perf_domain_rcu(struct rcu_head *rp) * 1. an Energy Model (EM) is available; * 2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy. * 3. the EM complexity is low enough to keep scheduling overheads low; + * 4. schedutil is driving the frequency of all CPUs of the rd; * * The complexity of the Energy Model is defined as: * @@ -294,12 +298,15 @@ static void destroy_perf_domain_rcu(struct rcu_head *rp) */ #define EM_MAX_COMPLEXITY 2048 +extern struct cpufreq_governor schedutil_gov; static void build_perf_domains(const struct cpumask *cpu_map) { int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map); struct perf_domain *pd = NULL, *tmp; int cpu = cpumask_first(cpu_map); struct root_domain *rd = cpu_rq(cpu)->rd; + struct cpufreq_policy *policy; + struct cpufreq_governor *gov; /* EAS is enabled for asymmetric CPU capacity topologies. */ if (!per_cpu(sd_asym_cpucapacity, cpu)) { @@ -315,6 +322,19 @@ static void build_perf_domains(const struct cpumask *cpu_map) if (find_pd(pd, i)) continue; + /* Do not attempt EAS if schedutil is not being used. */ + policy = cpufreq_cpu_get(i); + if (!policy) + goto free; + gov = policy->governor; + cpufreq_cpu_put(policy); + if (gov != &schedutil_gov) { + if (rd->pd) + pr_warn("rd %*pbl: Disabling EAS, schedutil is mandatory\n", + cpumask_pr_args(cpu_map)); + goto free; + } + /* Create the new pd and add it to the local list. */ tmp = pd_init(i); if (!tmp) @@ -356,7 +376,7 @@ free: } #else static void free_pd(struct perf_domain *pd) { } -#endif /* CONFIG_ENERGY_MODEL */ +#endif /* CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL*/ static void free_rootdomain(struct rcu_head *rcu) { @@ -2152,10 +2172,10 @@ match2: ; } -#ifdef CONFIG_ENERGY_MODEL +#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) /* Build perf. domains: */ for (i = 0; i < ndoms_new; i++) { - for (j = 0; j < n; j++) { + for (j = 0; j < n && !sched_energy_update; j++) { if (cpumask_equal(doms_new[i], doms_cur[j]) && cpu_rq(cpumask_first(doms_cur[j]))->rd->pd) goto match3; From 1f74de8798c93ce14801cc4e772603e51c841c33 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:22 +0000 Subject: [PATCH 19/23] sched/toplogy: Introduce the 'sched_energy_present' static key In order to make sure Energy Aware Scheduling (EAS) will not impact systems where no Energy Model is available, introduce a static key guarding the access to EAS code. Since EAS is enabled on a per-root-domain basis, the static key is enabled when at least one root domain meets all conditions for EAS. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-10-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/sched.h | 4 ++++ kernel/sched/topology.c | 28 ++++++++++++++++++++++++---- 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index fd84900b0b21..2b3cf356e958 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2296,3 +2296,7 @@ unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned #else #define perf_domain_span(pd) NULL #endif + +#ifdef CONFIG_SMP +extern struct static_key_false sched_energy_present; +#endif diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 0a5a1d3a4eae..3f35ba1d8fde 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -201,6 +201,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) return 1; } +DEFINE_STATIC_KEY_FALSE(sched_energy_present); #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) DEFINE_MUTEX(sched_energy_mutex); bool sched_energy_update; @@ -273,6 +274,19 @@ static void destroy_perf_domain_rcu(struct rcu_head *rp) free_pd(pd); } +static void sched_energy_set(bool has_eas) +{ + if (!has_eas && static_branch_unlikely(&sched_energy_present)) { + if (sched_debug()) + pr_info("%s: stopping EAS\n", __func__); + static_branch_disable_cpuslocked(&sched_energy_present); + } else if (has_eas && !static_branch_unlikely(&sched_energy_present)) { + if (sched_debug()) + pr_info("%s: starting EAS\n", __func__); + static_branch_enable_cpuslocked(&sched_energy_present); + } +} + /* * EAS can be used on a root domain if it meets all the following conditions: * 1. an Energy Model (EM) is available; @@ -299,7 +313,7 @@ static void destroy_perf_domain_rcu(struct rcu_head *rp) #define EM_MAX_COMPLEXITY 2048 extern struct cpufreq_governor schedutil_gov; -static void build_perf_domains(const struct cpumask *cpu_map) +static bool build_perf_domains(const struct cpumask *cpu_map) { int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map); struct perf_domain *pd = NULL, *tmp; @@ -365,7 +379,7 @@ static void build_perf_domains(const struct cpumask *cpu_map) if (tmp) call_rcu(&tmp->rcu, destroy_perf_domain_rcu); - return; + return !!pd; free: free_pd(pd); @@ -373,6 +387,8 @@ free: rcu_assign_pointer(rd->pd, NULL); if (tmp) call_rcu(&tmp->rcu, destroy_perf_domain_rcu); + + return false; } #else static void free_pd(struct perf_domain *pd) { } @@ -2114,6 +2130,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { + bool __maybe_unused has_eas = false; int i, j, n; int new_topology; @@ -2177,14 +2194,17 @@ match2: for (i = 0; i < ndoms_new; i++) { for (j = 0; j < n && !sched_energy_update; j++) { if (cpumask_equal(doms_new[i], doms_cur[j]) && - cpu_rq(cpumask_first(doms_cur[j]))->rd->pd) + cpu_rq(cpumask_first(doms_cur[j]))->rd->pd) { + has_eas = true; goto match3; + } } /* No match - add perf. domains for a new rd */ - build_perf_domains(doms_new[i]); + has_eas |= build_perf_domains(doms_new[i]); match3: ; } + sched_energy_set(has_eas); #endif /* Remember the new sched domains: */ From 630246a06ae2a7a12d1fce85f1e5681032982791 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:24 +0000 Subject: [PATCH 20/23] sched/fair: Clean-up update_sg_lb_stats parameters In preparation for the introduction of a new root domain flag which can be set during load balance (the 'overutilized' flag), clean-up the set of parameters passed to update_sg_lb_stats(). More specifically, the 'local_group' and 'local_idx' parameters can be removed since they can easily be reconstructed from within the function. While at it, transform the 'overload' parameter into a flag stored in the 'sg_status' parameter hence facilitating the definition of new flags when needed. Suggested-by: Peter Zijlstra Suggested-by: Valentin Schneider Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-12-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 27 +++++++++++---------------- kernel/sched/sched.h | 3 +++ 2 files changed, 14 insertions(+), 16 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a31a6d325901..e04f29098ec7 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7905,16 +7905,16 @@ static bool update_nohz_stats(struct rq *rq, bool force) * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. * @group: sched_group whose statistics are to be updated. - * @load_idx: Load index of sched_domain of this_cpu for load calc. - * @local_group: Does group contain this_cpu. * @sgs: variable to hold the statistics for this group. - * @overload: Indicate pullable load (e.g. >1 runnable task). + * @sg_status: Holds flag indicating the status of the sched_group */ static inline void update_sg_lb_stats(struct lb_env *env, - struct sched_group *group, int load_idx, - int local_group, struct sg_lb_stats *sgs, - bool *overload) + struct sched_group *group, + struct sg_lb_stats *sgs, + int *sg_status) { + int local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group)); + int load_idx = get_sd_load_idx(env->sd, env->idle); unsigned long load; int i, nr_running; @@ -7938,7 +7938,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, nr_running = rq->nr_running; if (nr_running > 1) - *overload = true; + *sg_status |= SG_OVERLOAD; #ifdef CONFIG_NUMA_BALANCING sgs->nr_numa_running += rq->nr_numa_running; @@ -7954,7 +7954,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, if (env->sd->flags & SD_ASYM_CPUCAPACITY && sgs->group_misfit_task_load < rq->misfit_task_load) { sgs->group_misfit_task_load = rq->misfit_task_load; - *overload = 1; + *sg_status |= SG_OVERLOAD; } } @@ -8099,17 +8099,14 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sched_group *sg = env->sd->groups; struct sg_lb_stats *local = &sds->local_stat; struct sg_lb_stats tmp_sgs; - int load_idx; - bool overload = false; bool prefer_sibling = child && child->flags & SD_PREFER_SIBLING; + int sg_status = 0; #ifdef CONFIG_NO_HZ_COMMON if (env->idle == CPU_NEWLY_IDLE && READ_ONCE(nohz.has_blocked)) env->flags |= LBF_NOHZ_STATS; #endif - load_idx = get_sd_load_idx(env->sd, env->idle); - do { struct sg_lb_stats *sgs = &tmp_sgs; int local_group; @@ -8124,8 +8121,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd update_group_capacity(env->sd, env->dst_cpu); } - update_sg_lb_stats(env, sg, load_idx, local_group, sgs, - &overload); + update_sg_lb_stats(env, sg, sgs, &sg_status); if (local_group) goto next_group; @@ -8175,8 +8171,7 @@ next_group: if (!env->sd->parent) { /* update overload indicator if we are at root domain */ - if (READ_ONCE(env->dst_rq->rd->overload) != overload) - WRITE_ONCE(env->dst_rq->rd->overload, overload); + WRITE_ONCE(env->dst_rq->rd->overload, sg_status & SG_OVERLOAD); } } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 2b3cf356e958..d4d984846924 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -716,6 +716,9 @@ struct perf_domain { struct rcu_head rcu; }; +/* Scheduling group status flags */ +#define SG_OVERLOAD 0x1 /* More than one runnable task on a CPU. */ + /* * We add the notion of a root-domain which will be used to define per-domain * variables. Each exclusive cpuset essentially defines an island domain by From 2802bf3cd936fe2c8033a696d375a4d9d3974de4 Mon Sep 17 00:00:00 2001 From: Morten Rasmussen Date: Mon, 3 Dec 2018 09:56:25 +0000 Subject: [PATCH 21/23] sched/fair: Add over-utilization/tipping point indicator Energy-aware scheduling is only meant to be active while the system is _not_ over-utilized. That is, there are spare cycles available to shift tasks around based on their actual utilization to get a more energy-efficient task distribution without depriving any tasks. When above the tipping point task placement is done the traditional way based on load_avg, spreading the tasks across as many cpus as possible based on priority scaled load to preserve smp_nice. Below the tipping point we want to use util_avg instead. We need to define a criteria for when we make the switch. The util_avg for each cpu converges towards 100% regardless of how many additional tasks we may put on it. If we define over-utilized as: sum_{cpus}(rq.cfs.avg.util_avg) + margin > sum_{cpus}(rq.capacity) some individual cpus may be over-utilized running multiple tasks even when the above condition is false. That should be okay as long as we try to spread the tasks out to avoid per-cpu over-utilization as much as possible and if all tasks have the _same_ priority. If the latter isn't true, we have to consider priority to preserve smp_nice. For example, we could have n_cpus nice=-10 util_avg=55% tasks and n_cpus/2 nice=0 util_avg=60% tasks. Balancing based on util_avg we are likely to end up with nice=-10 tasks sharing cpus and nice=0 tasks getting their own as we 1.5*n_cpus tasks in total and 55%+55% is less over-utilized than 55%+60% for those cpus that have to be shared. The system utilization is only 85% of the system capacity, but we are breaking smp_nice. To be sure not to break smp_nice, we have defined over-utilization conservatively as when any cpu in the system is fully utilized at its highest frequency instead: cpu_rq(any).cfs.avg.util_avg + margin > cpu_rq(any).capacity IOW, as soon as one cpu is (nearly) 100% utilized, we switch to load_avg to factor in priority to preserve smp_nice. With this definition, we can skip periodic load-balance as no cpu has an always-running task when the system is not over-utilized. All tasks will be periodic and we can balance them at wake-up. This conservative condition does however mean that some scenarios that could benefit from energy-aware decisions even if one cpu is fully utilized would not get those benefits. For systems where some cpus might have reduced capacity on some cpus (RT-pressure and/or big.LITTLE), we want periodic load-balance checks as soon a just a single cpu is fully utilized as it might one of those with reduced capacity and in that case we want to migrate it. [ peterz: Added a comment explaining why new tasks are not accounted during overutilization detection. ] Signed-off-by: Morten Rasmussen Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-13-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 59 ++++++++++++++++++++++++++++++++++++++++++-- kernel/sched/sched.h | 4 +++ 2 files changed, 61 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e04f29098ec7..767e7675774b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5082,6 +5082,24 @@ static inline void hrtick_update(struct rq *rq) } #endif +#ifdef CONFIG_SMP +static inline unsigned long cpu_util(int cpu); +static unsigned long capacity_of(int cpu); + +static inline bool cpu_overutilized(int cpu) +{ + return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin); +} + +static inline void update_overutilized_status(struct rq *rq) +{ + if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) + WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED); +} +#else +static inline void update_overutilized_status(struct rq *rq) { } +#endif + /* * The enqueue_task method is called before nr_running is * increased. Here we update the fair scheduling stats and @@ -5139,8 +5157,26 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) update_cfs_group(se); } - if (!se) + if (!se) { add_nr_running(rq, 1); + /* + * Since new tasks are assigned an initial util_avg equal to + * half of the spare capacity of their CPU, tiny tasks have the + * ability to cross the overutilized threshold, which will + * result in the load balancer ruining all the task placement + * done by EAS. As a way to mitigate that effect, do not account + * for the first enqueue operation of new tasks during the + * overutilized flag detection. + * + * A better way of solving this problem would be to wait for + * the PELT signals of tasks to converge before taking them + * into account, but that is not straightforward to implement, + * and the following generally works well enough in practice. + */ + if (flags & ENQUEUE_WAKEUP) + update_overutilized_status(rq); + + } hrtick_update(rq); } @@ -7940,6 +7976,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, if (nr_running > 1) *sg_status |= SG_OVERLOAD; + if (cpu_overutilized(i)) + *sg_status |= SG_OVERUTILIZED; + #ifdef CONFIG_NUMA_BALANCING sgs->nr_numa_running += rq->nr_numa_running; sgs->nr_preferred_running += rq->nr_preferred_running; @@ -8170,8 +8209,15 @@ next_group: env->fbq_type = fbq_classify_group(&sds->busiest_stat); if (!env->sd->parent) { + struct root_domain *rd = env->dst_rq->rd; + /* update overload indicator if we are at root domain */ - WRITE_ONCE(env->dst_rq->rd->overload, sg_status & SG_OVERLOAD); + WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD); + + /* Update over-utilization (tipping point, U >= 0) indicator */ + WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED); + } else if (sg_status & SG_OVERUTILIZED) { + WRITE_ONCE(env->dst_rq->rd->overutilized, SG_OVERUTILIZED); } } @@ -8398,6 +8444,14 @@ static struct sched_group *find_busiest_group(struct lb_env *env) * this level. */ update_sd_lb_stats(env, &sds); + + if (static_branch_unlikely(&sched_energy_present)) { + struct root_domain *rd = env->dst_rq->rd; + + if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized)) + goto out_balanced; + } + local = &sds.local_stat; busiest = &sds.busiest_stat; @@ -9798,6 +9852,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) task_tick_numa(rq, curr); update_misfit_status(curr, rq); + update_overutilized_status(task_rq(curr)); } /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d4d984846924..0ba08924e017 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -718,6 +718,7 @@ struct perf_domain { /* Scheduling group status flags */ #define SG_OVERLOAD 0x1 /* More than one runnable task on a CPU. */ +#define SG_OVERUTILIZED 0x2 /* One or more CPUs are over-utilized. */ /* * We add the notion of a root-domain which will be used to define per-domain @@ -741,6 +742,9 @@ struct root_domain { */ int overload; + /* Indicate one or more cpus over-utilized (tipping point) */ + int overutilized; + /* * The bit corresponding to a CPU gets set here if such CPU has more * than one runnable -deadline task (as it is below for RT tasks). From 390031e4c309c94ecc07a558187eb5185200df83 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:26 +0000 Subject: [PATCH 22/23] sched/fair: Introduce an energy estimation helper function In preparation for the definition of an energy-aware wakeup path, introduce a helper function to estimate the consequence on system energy when a specific task wakes-up on a specific CPU. compute_energy() estimates the capacity state to be reached by all performance domains and estimates the consumption of each online CPU according to its Energy Model and its percentage of busy time. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-14-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 76 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 767e7675774b..b3c94584d947 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6377,6 +6377,82 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) return !task_fits_capacity(p, min_cap); } +/* + * Predicts what cpu_util(@cpu) would return if @p was migrated (and enqueued) + * to @dst_cpu. + */ +static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) +{ + struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs; + unsigned long util_est, util = READ_ONCE(cfs_rq->avg.util_avg); + + /* + * If @p migrates from @cpu to another, remove its contribution. Or, + * if @p migrates from another CPU to @cpu, add its contribution. In + * the other cases, @cpu is not impacted by the migration, so the + * util_avg should already be correct. + */ + if (task_cpu(p) == cpu && dst_cpu != cpu) + sub_positive(&util, task_util(p)); + else if (task_cpu(p) != cpu && dst_cpu == cpu) + util += task_util(p); + + if (sched_feat(UTIL_EST)) { + util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued); + + /* + * During wake-up, the task isn't enqueued yet and doesn't + * appear in the cfs_rq->avg.util_est.enqueued of any rq, + * so just add it (if needed) to "simulate" what will be + * cpu_util() after the task has been enqueued. + */ + if (dst_cpu == cpu) + util_est += _task_util_est(p); + + util = max(util, util_est); + } + + return min(util, capacity_orig_of(cpu)); +} + +/* + * compute_energy(): Estimates the energy that would be consumed if @p was + * migrated to @dst_cpu. compute_energy() predicts what will be the utilization + * landscape of the * CPUs after the task migration, and uses the Energy Model + * to compute what would be the energy if we decided to actually migrate that + * task. + */ +static long +compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) +{ + long util, max_util, sum_util, energy = 0; + int cpu; + + for (; pd; pd = pd->next) { + max_util = sum_util = 0; + /* + * The capacity state of CPUs of the current rd can be driven by + * CPUs of another rd if they belong to the same performance + * domain. So, account for the utilization of these CPUs too + * by masking pd with cpu_online_mask instead of the rd span. + * + * If an entire performance domain is outside of the current rd, + * it will not appear in its pd list and will not be accounted + * by compute_energy(). + */ + for_each_cpu_and(cpu, perf_domain_span(pd), cpu_online_mask) { + util = cpu_util_next(cpu, p, dst_cpu); + util = schedutil_energy_util(cpu, util); + max_util = max(util, max_util); + sum_util += util; + } + + energy += em_pd_energy(pd->em_pd, max_util, sum_util); + } + + return energy; +} + /* * select_task_rq_fair: Select target runqueue for the waking task in domains * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE, From 732cd75b8c920d3727e69957b14faa7c2d7c3b75 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:27 +0000 Subject: [PATCH 23/23] sched/fair: Select an energy-efficient CPU on task wake-up If an Energy Model (EM) is available and if the system isn't overutilized, re-route waking tasks into an energy-aware placement algorithm. The selection of an energy-efficient CPU for a task is achieved by estimating the impact on system-level active energy resulting from the placement of the task on the CPU with the highest spare capacity in each performance domain. This strategy spreads tasks in a performance domain and avoids overly aggressive task packing. The best CPU energy-wise is then selected if it saves a large enough amount of energy with respect to prev_cpu. Although it has already shown significant benefits on some existing targets, this approach cannot scale to platforms with numerous CPUs. This is an attempt to do something useful as writing a fast heuristic that performs reasonably well on a broad spectrum of architectures isn't an easy task. As such, the scope of usability of the energy-aware wake-up path is restricted to systems with the SD_ASYM_CPUCAPACITY flag set, and where the EM isn't too complex. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-15-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 143 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 141 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index b3c94584d947..ca469646ebe1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6453,6 +6453,137 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) return energy; } +/* + * find_energy_efficient_cpu(): Find most energy-efficient target CPU for the + * waking task. find_energy_efficient_cpu() looks for the CPU with maximum + * spare capacity in each performance domain and uses it as a potential + * candidate to execute the task. Then, it uses the Energy Model to figure + * out which of the CPU candidates is the most energy-efficient. + * + * The rationale for this heuristic is as follows. In a performance domain, + * all the most energy efficient CPU candidates (according to the Energy + * Model) are those for which we'll request a low frequency. When there are + * several CPUs for which the frequency request will be the same, we don't + * have enough data to break the tie between them, because the Energy Model + * only includes active power costs. With this model, if we assume that + * frequency requests follow utilization (e.g. using schedutil), the CPU with + * the maximum spare capacity in a performance domain is guaranteed to be among + * the best candidates of the performance domain. + * + * In practice, it could be preferable from an energy standpoint to pack + * small tasks on a CPU in order to let other CPUs go in deeper idle states, + * but that could also hurt our chances to go cluster idle, and we have no + * ways to tell with the current Energy Model if this is actually a good + * idea or not. So, find_energy_efficient_cpu() basically favors + * cluster-packing, and spreading inside a cluster. That should at least be + * a good thing for latency, and this is consistent with the idea that most + * of the energy savings of EAS come from the asymmetry of the system, and + * not so much from breaking the tie between identical CPUs. That's also the + * reason why EAS is enabled in the topology code only for systems where + * SD_ASYM_CPUCAPACITY is set. + * + * NOTE: Forkees are not accepted in the energy-aware wake-up path because + * they don't have any useful utilization data yet and it's not possible to + * forecast their impact on energy consumption. Consequently, they will be + * placed by find_idlest_cpu() on the least loaded CPU, which might turn out + * to be energy-inefficient in some use-cases. The alternative would be to + * bias new tasks towards specific types of CPUs first, or to try to infer + * their util_avg from the parent task, but those heuristics could hurt + * other use-cases too. So, until someone finds a better way to solve this, + * let's keep things simple by re-using the existing slow path. + */ + +static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) +{ + unsigned long prev_energy = ULONG_MAX, best_energy = ULONG_MAX; + struct root_domain *rd = cpu_rq(smp_processor_id())->rd; + int cpu, best_energy_cpu = prev_cpu; + struct perf_domain *head, *pd; + unsigned long cpu_cap, util; + struct sched_domain *sd; + + rcu_read_lock(); + pd = rcu_dereference(rd->pd); + if (!pd || READ_ONCE(rd->overutilized)) + goto fail; + head = pd; + + /* + * Energy-aware wake-up happens on the lowest sched_domain starting + * from sd_asym_cpucapacity spanning over this_cpu and prev_cpu. + */ + sd = rcu_dereference(*this_cpu_ptr(&sd_asym_cpucapacity)); + while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) + sd = sd->parent; + if (!sd) + goto fail; + + sync_entity_load_avg(&p->se); + if (!task_util_est(p)) + goto unlock; + + for (; pd; pd = pd->next) { + unsigned long cur_energy, spare_cap, max_spare_cap = 0; + int max_spare_cap_cpu = -1; + + for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { + if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + continue; + + /* Skip CPUs that will be overutilized. */ + util = cpu_util_next(cpu, p, cpu); + cpu_cap = capacity_of(cpu); + if (cpu_cap * 1024 < util * capacity_margin) + continue; + + /* Always use prev_cpu as a candidate. */ + if (cpu == prev_cpu) { + prev_energy = compute_energy(p, prev_cpu, head); + best_energy = min(best_energy, prev_energy); + continue; + } + + /* + * Find the CPU with the maximum spare capacity in + * the performance domain + */ + spare_cap = cpu_cap - util; + if (spare_cap > max_spare_cap) { + max_spare_cap = spare_cap; + max_spare_cap_cpu = cpu; + } + } + + /* Evaluate the energy impact of using this CPU. */ + if (max_spare_cap_cpu >= 0) { + cur_energy = compute_energy(p, max_spare_cap_cpu, head); + if (cur_energy < best_energy) { + best_energy = cur_energy; + best_energy_cpu = max_spare_cap_cpu; + } + } + } +unlock: + rcu_read_unlock(); + + /* + * Pick the best CPU if prev_cpu cannot be used, or if it saves at + * least 6% of the energy used by prev_cpu. + */ + if (prev_energy == ULONG_MAX) + return best_energy_cpu; + + if ((prev_energy - best_energy) > (prev_energy >> 4)) + return best_energy_cpu; + + return prev_cpu; + +fail: + rcu_read_unlock(); + + return -1; +} + /* * select_task_rq_fair: Select target runqueue for the waking task in domains * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE, @@ -6476,8 +6607,16 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (sd_flag & SD_BALANCE_WAKE) { record_wakee(p); - want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) - && cpumask_test_cpu(cpu, &p->cpus_allowed); + + if (static_branch_unlikely(&sched_energy_present)) { + new_cpu = find_energy_efficient_cpu(p, prev_cpu); + if (new_cpu >= 0) + return new_cpu; + new_cpu = prev_cpu; + } + + want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) && + cpumask_test_cpu(cpu, &p->cpus_allowed); } rcu_read_lock();