From 2fb75e1b642f49253d8848c9e47e8942f5366221 Mon Sep 17 00:00:00 2001 From: Liu Xinpeng Date: Mon, 25 Oct 2021 11:46:26 +0800 Subject: psi: Add a missing SPDX license header Add the missing SPDX license header to include/linux/psi.h include/linux/psi_types.h kernel/sched/psi.c Signed-off-by: Liu Xinpeng Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/1635133586-84611-2-git-send-email-liuxp11@chinatelecom.cn --- include/linux/psi.h | 1 + include/linux/psi_types.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/psi.h b/include/linux/psi.h index 65eb1476ac70..a70ca833c6d7 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 0a23300d49af..bf50068d5d4b 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PSI_TYPES_H #define _LINUX_PSI_TYPES_H -- cgit v1.2.3-59-g8ed1b From 4feee7d12603deca8775f9f9ae5e121093837444 Mon Sep 17 00:00:00 2001 From: Josh Don Date: Mon, 18 Oct 2021 13:34:28 -0700 Subject: sched/core: Forced idle accounting Adds accounting for "forced idle" time, which is time where a cookie'd task forces its SMT sibling to idle, despite the presence of runnable tasks. Forced idle time is one means to measure the cost of enabling core scheduling (ie. the capacity lost due to the need to force idle). Forced idle time is attributed to the thread responsible for causing the forced idle. A few details: - Forced idle time is displayed via /proc/PID/sched. It also requires that schedstats is enabled. - Forced idle is only accounted when a sibling hyperthread is held idle despite the presence of runnable tasks. No time is charged if a sibling is idle but has no runnable tasks. - Tasks with 0 cookie are never charged forced idle. - For SMT > 2, we scale the amount of forced idle charged based on the number of forced idle siblings. Additionally, we split the time up and evenly charge it to all running tasks, as each is equally responsible for the forced idle. Signed-off-by: Josh Don Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20211018203428.2025792-1-joshdon@google.com --- include/linux/sched.h | 4 +++ kernel/sched/core.c | 82 +++++++++++++++++++++++++++++++++++------------ kernel/sched/core_sched.c | 66 +++++++++++++++++++++++++++++++++++++- kernel/sched/debug.c | 4 +++ kernel/sched/fair.c | 2 +- kernel/sched/sched.h | 32 ++++++++++++++++-- 6 files changed, 166 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 78c351e35fec..d2e261adb8ea 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -523,7 +523,11 @@ struct sched_statistics { u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; + +#ifdef CONFIG_SCHED_CORE + u64 core_forceidle_sum; #endif +#endif /* CONFIG_SCHEDSTATS */ } ____cacheline_aligned; struct sched_entity { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3c9b0fda64ac..beaa8be6241e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -144,7 +144,7 @@ static inline bool __sched_core_less(struct task_struct *a, struct task_struct * return false; /* flip prio, so high prio is leftmost */ - if (prio_less(b, a, task_rq(a)->core->core_forceidle)) + if (prio_less(b, a, !!task_rq(a)->core->core_forceidle_count)) return true; return false; @@ -181,15 +181,23 @@ void sched_core_enqueue(struct rq *rq, struct task_struct *p) rb_add(&p->core_node, &rq->core_tree, rb_sched_core_less); } -void sched_core_dequeue(struct rq *rq, struct task_struct *p) +void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { rq->core->core_task_seq++; - if (!sched_core_enqueued(p)) - return; + if (sched_core_enqueued(p)) { + rb_erase(&p->core_node, &rq->core_tree); + RB_CLEAR_NODE(&p->core_node); + } - rb_erase(&p->core_node, &rq->core_tree); - RB_CLEAR_NODE(&p->core_node); + /* + * Migrating the last task off the cpu, with the cpu in forced idle + * state. Reschedule to create an accounting edge for forced idle, + * and re-examine whether the core is still in forced idle state. + */ + if (!(flags & DEQUEUE_SAVE) && rq->nr_running == 1 && + rq->core->core_forceidle_count && rq->curr == rq->idle) + resched_curr(rq); } /* @@ -280,6 +288,8 @@ static void __sched_core_flip(bool enabled) for_each_cpu(t, smt_mask) cpu_rq(t)->core_enabled = enabled; + cpu_rq(cpu)->core->core_forceidle_start = 0; + sched_core_unlock(cpu, &flags); cpumask_andnot(&sched_core_mask, &sched_core_mask, smt_mask); @@ -364,7 +374,8 @@ void sched_core_put(void) #else /* !CONFIG_SCHED_CORE */ static inline void sched_core_enqueue(struct rq *rq, struct task_struct *p) { } -static inline void sched_core_dequeue(struct rq *rq, struct task_struct *p) { } +static inline void +sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { } #endif /* CONFIG_SCHED_CORE */ @@ -2005,7 +2016,7 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) { if (sched_core_enabled(rq)) - sched_core_dequeue(rq, p); + sched_core_dequeue(rq, p, flags); if (!(flags & DEQUEUE_NOCLOCK)) update_rq_clock(rq); @@ -5244,6 +5255,7 @@ void scheduler_tick(void) if (sched_feat(LATENCY_WARN)) resched_latency = cpu_resched_latency(rq); calc_global_load_tick(rq); + sched_core_tick(rq); rq_unlock(rq, &rf); @@ -5656,6 +5668,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) struct task_struct *next, *p, *max = NULL; const struct cpumask *smt_mask; bool fi_before = false; + bool core_clock_updated = (rq == rq->core); unsigned long cookie; int i, cpu, occ = 0; struct rq *rq_i; @@ -5708,10 +5721,18 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) /* reset state */ rq->core->core_cookie = 0UL; - if (rq->core->core_forceidle) { + if (rq->core->core_forceidle_count) { + if (!core_clock_updated) { + update_rq_clock(rq->core); + core_clock_updated = true; + } + sched_core_account_forceidle(rq); + /* reset after accounting force idle */ + rq->core->core_forceidle_start = 0; + rq->core->core_forceidle_count = 0; + rq->core->core_forceidle_occupation = 0; need_sync = true; fi_before = true; - rq->core->core_forceidle = false; } /* @@ -5753,7 +5774,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) for_each_cpu_wrap(i, smt_mask, cpu) { rq_i = cpu_rq(i); - if (i != cpu) + /* + * Current cpu always has its clock updated on entrance to + * pick_next_task(). If the current cpu is not the core, + * the core may also have been updated above. + */ + if (i != cpu && (rq_i != rq->core || !core_clock_updated)) update_rq_clock(rq_i); p = rq_i->core_pick = pick_task(rq_i); @@ -5783,7 +5809,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) if (p == rq_i->idle) { if (rq_i->nr_running) { - rq->core->core_forceidle = true; + rq->core->core_forceidle_count++; if (!fi_before) rq->core->core_forceidle_seq++; } @@ -5792,6 +5818,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } } + if (schedstat_enabled() && rq->core->core_forceidle_count) { + if (cookie) + rq->core->core_forceidle_start = rq_clock(rq->core); + rq->core->core_forceidle_occupation = occ; + } + rq->core->core_pick_seq = rq->core->core_task_seq; next = rq->core_pick; rq->core_sched_seq = rq->core->core_pick_seq; @@ -5828,8 +5860,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * 1 0 1 * 1 1 0 */ - if (!(fi_before && rq->core->core_forceidle)) - task_vruntime_update(rq_i, rq_i->core_pick, rq->core->core_forceidle); + if (!(fi_before && rq->core->core_forceidle_count)) + task_vruntime_update(rq_i, rq_i->core_pick, !!rq->core->core_forceidle_count); rq_i->core_pick->core_occupation = occ; @@ -6033,11 +6065,19 @@ static void sched_core_cpu_deactivate(unsigned int cpu) goto unlock; /* copy the shared state to the new leader */ - core_rq->core_task_seq = rq->core_task_seq; - core_rq->core_pick_seq = rq->core_pick_seq; - core_rq->core_cookie = rq->core_cookie; - core_rq->core_forceidle = rq->core_forceidle; - core_rq->core_forceidle_seq = rq->core_forceidle_seq; + core_rq->core_task_seq = rq->core_task_seq; + core_rq->core_pick_seq = rq->core_pick_seq; + core_rq->core_cookie = rq->core_cookie; + core_rq->core_forceidle_count = rq->core_forceidle_count; + core_rq->core_forceidle_seq = rq->core_forceidle_seq; + core_rq->core_forceidle_occupation = rq->core_forceidle_occupation; + + /* + * Accounting edge for forced idle is handled in pick_next_task(). + * Don't need another one here, since the hotplug thread shouldn't + * have a cookie. + */ + core_rq->core_forceidle_start = 0; /* install new leader */ for_each_cpu(t, smt_mask) { @@ -9413,7 +9453,9 @@ void __init sched_init(void) rq->core_pick = NULL; rq->core_enabled = 0; rq->core_tree = RB_ROOT; - rq->core_forceidle = false; + rq->core_forceidle_count = 0; + rq->core_forceidle_occupation = 0; + rq->core_forceidle_start = 0; rq->core_cookie = 0UL; #endif diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 517f72b008f5..1fb45672ec85 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -73,7 +73,7 @@ static unsigned long sched_core_update_cookie(struct task_struct *p, enqueued = sched_core_enqueued(p); if (enqueued) - sched_core_dequeue(rq, p); + sched_core_dequeue(rq, p, DEQUEUE_SAVE); old_cookie = p->core_cookie; p->core_cookie = cookie; @@ -85,6 +85,10 @@ static unsigned long sched_core_update_cookie(struct task_struct *p, * If task is currently running, it may not be compatible anymore after * the cookie change, so enter the scheduler on its CPU to schedule it * away. + * + * Note that it is possible that as a result of this cookie change, the + * core has now entered/left forced idle state. Defer accounting to the + * next scheduling edge, rather than always forcing a reschedule here. */ if (task_running(rq, p)) resched_curr(rq); @@ -232,3 +236,63 @@ out: return err; } +#ifdef CONFIG_SCHEDSTATS + +/* REQUIRES: rq->core's clock recently updated. */ +void __sched_core_account_forceidle(struct rq *rq) +{ + const struct cpumask *smt_mask = cpu_smt_mask(cpu_of(rq)); + u64 delta, now = rq_clock(rq->core); + struct rq *rq_i; + struct task_struct *p; + int i; + + lockdep_assert_rq_held(rq); + + WARN_ON_ONCE(!rq->core->core_forceidle_count); + + if (rq->core->core_forceidle_start == 0) + return; + + delta = now - rq->core->core_forceidle_start; + if (unlikely((s64)delta <= 0)) + return; + + rq->core->core_forceidle_start = now; + + if (WARN_ON_ONCE(!rq->core->core_forceidle_occupation)) { + /* can't be forced idle without a running task */ + } else if (rq->core->core_forceidle_count > 1 || + rq->core->core_forceidle_occupation > 1) { + /* + * For larger SMT configurations, we need to scale the charged + * forced idle amount since there can be more than one forced + * idle sibling and more than one running cookied task. + */ + delta *= rq->core->core_forceidle_count; + delta = div_u64(delta, rq->core->core_forceidle_occupation); + } + + for_each_cpu(i, smt_mask) { + rq_i = cpu_rq(i); + p = rq_i->core_pick ?: rq_i->curr; + + if (!p->core_cookie) + continue; + + __schedstat_add(p->stats.core_forceidle_sum, delta); + } +} + +void __sched_core_tick(struct rq *rq) +{ + if (!rq->core->core_forceidle_count) + return; + + if (rq != rq->core) + update_rq_clock(rq->core); + + __sched_core_account_forceidle(rq); +} + +#endif /* CONFIG_SCHEDSTATS */ diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 7dcbaa31c5d9..aa29211de1bf 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1023,6 +1023,10 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, __PN(avg_atom); __PN(avg_per_cpu); + +#ifdef CONFIG_SCHED_CORE + PN_SCHEDSTAT(core_forceidle_sum); +#endif } __P(nr_switches); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6e476f6d9435..884f29d07963 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -11068,7 +11068,7 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) * MIN_NR_TASKS_DURING_FORCEIDLE - 1 tasks and use that to check * if we need to give up the CPU. */ - if (rq->core->core_forceidle && rq->cfs.nr_running == 1 && + if (rq->core->core_forceidle_count && rq->cfs.nr_running == 1 && __entity_slice_used(&curr->se, MIN_NR_TASKS_DURING_FORCEIDLE)) resched_curr(rq); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0e66749486e7..eb971151e7e4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1111,8 +1111,10 @@ struct rq { unsigned int core_task_seq; unsigned int core_pick_seq; unsigned long core_cookie; - unsigned char core_forceidle; + unsigned int core_forceidle_count; unsigned int core_forceidle_seq; + unsigned int core_forceidle_occupation; + u64 core_forceidle_start; #endif }; @@ -1253,7 +1255,7 @@ static inline bool sched_core_enqueued(struct task_struct *p) } extern void sched_core_enqueue(struct rq *rq, struct task_struct *p); -extern void sched_core_dequeue(struct rq *rq, struct task_struct *p); +extern void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags); extern void sched_core_get(void); extern void sched_core_put(void); @@ -1854,6 +1856,32 @@ static inline void flush_smp_call_function_from_idle(void) { } #include "stats.h" #include "autogroup.h" +#if defined(CONFIG_SCHED_CORE) && defined(CONFIG_SCHEDSTATS) + +extern void __sched_core_account_forceidle(struct rq *rq); + +static inline void sched_core_account_forceidle(struct rq *rq) +{ + if (schedstat_enabled()) + __sched_core_account_forceidle(rq); +} + +extern void __sched_core_tick(struct rq *rq); + +static inline void sched_core_tick(struct rq *rq) +{ + if (sched_core_enabled(rq) && schedstat_enabled()) + __sched_core_tick(rq); +} + +#else + +static inline void sched_core_account_forceidle(struct rq *rq) {} + +static inline void sched_core_tick(struct rq *rq) {} + +#endif /* CONFIG_SCHED_CORE && CONFIG_SCHEDSTATS */ + #ifdef CONFIG_CGROUP_SCHED /* -- cgit v1.2.3-59-g8ed1b From cb0e52b7748737b2cf6481fdd9b920ce7e1ebbdf Mon Sep 17 00:00:00 2001 From: Brian Chen Date: Wed, 10 Nov 2021 21:33:12 +0000 Subject: psi: Fix PSI_MEM_FULL state when tasks are in memstall and doing reclaim We've noticed cases where tasks in a cgroup are stalled on memory but there is little memory FULL pressure since tasks stay on the runqueue in reclaim. A simple example involves a single threaded program that keeps leaking and touching large amounts of memory. It runs in a cgroup with swap enabled, memory.high set at 10M and cpu.max ratio set at 5%. Though there is significant CPU pressure and memory SOME, there is barely any memory FULL since the task enters reclaim and stays on the runqueue. However, this memory-bound task is effectively stalled on memory and we expect memory FULL to match memory SOME in this scenario. The code is confused about memstall && running, thinking there is a stalled task and a productive task when there's only one task: a reclaimer that's counted as both. To fix this, we redefine the condition for PSI_MEM_FULL to check that all running tasks are in an active memstall instead of checking that there are no running tasks. case PSI_MEM_FULL: - return unlikely(tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]); + return unlikely(tasks[NR_MEMSTALL] && + tasks[NR_RUNNING] == tasks[NR_MEMSTALL_RUNNING]); This will capture reclaimers. It will also capture tasks that called psi_memstall_enter() and are about to sleep, but this should be negligible noise. Signed-off-by: Brian Chen Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20211110213312.310243-1-brianchen118@gmail.com --- include/linux/psi_types.h | 13 ++++++++++++- kernel/sched/psi.c | 45 ++++++++++++++++++++++++++++----------------- kernel/sched/stats.h | 5 ++++- 3 files changed, 44 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index bf50068d5d4b..516c0fe836fd 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -22,7 +22,17 @@ enum psi_task_count { * don't have to special case any state tracking for it. */ NR_ONCPU, - NR_PSI_TASK_COUNTS = 4, + /* + * For IO and CPU stalls the presence of running/oncpu tasks + * in the domain means a partial rather than a full stall. + * For memory it's not so simple because of page reclaimers: + * they are running/oncpu while representing a stall. To tell + * whether a domain has productivity left or not, we need to + * distinguish between regular running (i.e. productive) + * threads and memstall ones. + */ + NR_MEMSTALL_RUNNING, + NR_PSI_TASK_COUNTS = 5, }; /* Task state bitmasks */ @@ -30,6 +40,7 @@ enum psi_task_count { #define TSK_MEMSTALL (1 << NR_MEMSTALL) #define TSK_RUNNING (1 << NR_RUNNING) #define TSK_ONCPU (1 << NR_ONCPU) +#define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING) /* Resources that workloads could be stalled on */ enum psi_res { diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 3397fa001157..a679613a7cb7 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -35,13 +35,19 @@ * delayed on that resource such that nobody is advancing and the CPU * goes idle. This leaves both workload and CPU unproductive. * - * Naturally, the FULL state doesn't exist for the CPU resource at the - * system level, but exist at the cgroup level, means all non-idle tasks - * in a cgroup are delayed on the CPU resource which used by others outside - * of the cgroup or throttled by the cgroup cpu.max configuration. - * * SOME = nr_delayed_tasks != 0 - * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0 + * FULL = nr_delayed_tasks != 0 && nr_productive_tasks == 0 + * + * What it means for a task to be productive is defined differently + * for each resource. For IO, productive means a running task. For + * memory, productive means a running task that isn't a reclaimer. For + * CPU, productive means an oncpu task. + * + * Naturally, the FULL state doesn't exist for the CPU resource at the + * system level, but exist at the cgroup level. At the cgroup level, + * FULL means all non-idle tasks in the cgroup are delayed on the CPU + * resource which is being used by others outside of the cgroup or + * throttled by the cgroup cpu.max configuration. * * The percentage of wallclock time spent in those compound stall * states gives pressure numbers between 0 and 100 for each resource, @@ -82,13 +88,13 @@ * * threads = min(nr_nonidle_tasks, nr_cpus) * SOME = min(nr_delayed_tasks / threads, 1) - * FULL = (threads - min(nr_running_tasks, threads)) / threads + * FULL = (threads - min(nr_productive_tasks, threads)) / threads * * For the 257 number crunchers on 256 CPUs, this yields: * * threads = min(257, 256) * SOME = min(1 / 256, 1) = 0.4% - * FULL = (256 - min(257, 256)) / 256 = 0% + * FULL = (256 - min(256, 256)) / 256 = 0% * * For the 1 out of 4 memory-delayed tasks, this yields: * @@ -113,7 +119,7 @@ * For each runqueue, we track: * * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0) - * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu]) + * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_productive_tasks[cpu]) * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0) * * and then periodically aggregate: @@ -234,7 +240,8 @@ static bool test_state(unsigned int *tasks, enum psi_states state) case PSI_MEM_SOME: return unlikely(tasks[NR_MEMSTALL]); case PSI_MEM_FULL: - return unlikely(tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]); + return unlikely(tasks[NR_MEMSTALL] && + tasks[NR_RUNNING] == tasks[NR_MEMSTALL_RUNNING]); case PSI_CPU_SOME: return unlikely(tasks[NR_RUNNING] > tasks[NR_ONCPU]); case PSI_CPU_FULL: @@ -711,10 +718,11 @@ static void psi_group_change(struct psi_group *group, int cpu, if (groupc->tasks[t]) { groupc->tasks[t]--; } else if (!psi_bug) { - printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u] clear=%x set=%x\n", + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u %u] clear=%x set=%x\n", cpu, t, groupc->tasks[0], groupc->tasks[1], groupc->tasks[2], - groupc->tasks[3], clear, set); + groupc->tasks[3], groupc->tasks[4], + clear, set); psi_bug = 1; } } @@ -854,12 +862,15 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, int clear = TSK_ONCPU, set = 0; /* - * When we're going to sleep, psi_dequeue() lets us handle - * TSK_RUNNING and TSK_IOWAIT here, where we can combine it - * with TSK_ONCPU and save walking common ancestors twice. + * When we're going to sleep, psi_dequeue() lets us + * handle TSK_RUNNING, TSK_MEMSTALL_RUNNING and + * TSK_IOWAIT here, where we can combine it with + * TSK_ONCPU and save walking common ancestors twice. */ if (sleep) { clear |= TSK_RUNNING; + if (prev->in_memstall) + clear |= TSK_MEMSTALL_RUNNING; if (prev->in_iowait) set |= TSK_IOWAIT; } @@ -908,7 +919,7 @@ void psi_memstall_enter(unsigned long *flags) rq = this_rq_lock_irq(&rf); current->in_memstall = 1; - psi_task_change(current, 0, TSK_MEMSTALL); + psi_task_change(current, 0, TSK_MEMSTALL | TSK_MEMSTALL_RUNNING); rq_unlock_irq(rq, &rf); } @@ -937,7 +948,7 @@ void psi_memstall_leave(unsigned long *flags) rq = this_rq_lock_irq(&rf); current->in_memstall = 0; - psi_task_change(current, TSK_MEMSTALL, 0); + psi_task_change(current, TSK_MEMSTALL | TSK_MEMSTALL_RUNNING, 0); rq_unlock_irq(rq, &rf); } diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index cfb0893a83d4..3a3c826dd83a 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -118,6 +118,9 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup) if (static_branch_likely(&psi_disabled)) return; + if (p->in_memstall) + set |= TSK_MEMSTALL_RUNNING; + if (!wakeup || p->sched_psi_wake_requeue) { if (p->in_memstall) set |= TSK_MEMSTALL; @@ -148,7 +151,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) return; if (p->in_memstall) - clear |= TSK_MEMSTALL; + clear |= (TSK_MEMSTALL | TSK_MEMSTALL_RUNNING); psi_task_change(p, clear, 0); } -- cgit v1.2.3-59-g8ed1b