From 493afbd187c4c9cc1642792c0d9ba400c3d6d90d Mon Sep 17 00:00:00 2001 From: K Prateek Nayak Date: Thu, 28 Nov 2024 12:59:54 +0530 Subject: sched/fair: Fix NEXT_BUDDY Adam reports that enabling NEXT_BUDDY insta triggers a WARN in pick_next_entity(). Moving clear_buddies() up before the delayed dequeue bits ensures no ->next buddy becomes delayed. Further ensure no new ->next buddy ever starts as delayed. Fixes: 152e11f6df29 ("sched/fair: Implement delayed dequeue") Reported-by: Adam Li Signed-off-by: K Prateek Nayak Signed-off-by: Peter Zijlstra (Intel) Tested-by: Adam Li Link: https://lkml.kernel.org/r/670a0d54-e398-4b1f-8a6e-90784e2fdf89@amd.com --- kernel/sched/fair.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'kernel/sched/fair.c') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 05b8f1eb2c14..9d7a2dd2c260 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5478,6 +5478,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) bool sleep = flags & DEQUEUE_SLEEP; update_curr(cfs_rq); + clear_buddies(cfs_rq, se); if (flags & DEQUEUE_DELAYED) { SCHED_WARN_ON(!se->sched_delayed); @@ -5494,8 +5495,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (sched_feat(DELAY_DEQUEUE) && delay && !entity_eligible(cfs_rq, se)) { - if (cfs_rq->next == se) - cfs_rq->next = NULL; update_load_avg(cfs_rq, se, 0); se->sched_delayed = 1; return false; @@ -5520,8 +5519,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_stats_dequeue_fair(cfs_rq, se, flags); - clear_buddies(cfs_rq, se); - update_entity_lag(cfs_rq, se); if (sched_feat(PLACE_REL_DEADLINE) && !sleep) { se->deadline -= se->vruntime; @@ -8774,7 +8771,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int if (unlikely(throttled_hierarchy(cfs_rq_of(pse)))) return; - if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) { + if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK) && !pse->sched_delayed) { set_next_buddy(pse); } -- cgit v1.2.3 From 76f2f783294d7d55c2564e2dfb0a7279ba0bc264 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 2 Dec 2024 18:45:57 +0100 Subject: sched/eevdf: More PELT vs DELAYED_DEQUEUE Vincent and Dietmar noted that while commit fc1892becd56 ("sched/eevdf: Fixup PELT vs DELAYED_DEQUEUE") fixes the entity runnable stats, it does not adjust the cfs_rq runnable stats, which are based off of h_nr_running. Track h_nr_delayed such that we can discount those and adjust the signal. Fixes: fc1892becd56 ("sched/eevdf: Fixup PELT vs DELAYED_DEQUEUE") Closes: https://lore.kernel.org/lkml/a9a45193-d0c6-4ba2-a822-464ad30b550e@arm.com/ Closes: https://lore.kernel.org/lkml/CAKfTPtCNUvWE_GX5LyvTF-WdxUT=ZgvZZv-4t=eWntg5uOFqiQ@mail.gmail.com/ [ Fixes checkpatch warnings and rebased ] Signed-off-by: Peter Zijlstra (Intel) Reported-by: Dietmar Eggemann Reported-by: Vincent Guittot Signed-off-by: "Peter Zijlstra (Intel)" Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Tested-by: K Prateek Nayak Link: https://lore.kernel.org/r/20241202174606.4074512-3-vincent.guittot@linaro.org --- kernel/sched/debug.c | 1 + kernel/sched/fair.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++----- kernel/sched/pelt.c | 2 +- kernel/sched/sched.h | 8 ++++++-- 4 files changed, 54 insertions(+), 8 deletions(-) (limited to 'kernel/sched/fair.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index a48b2a701ec2..a1be00a988bf 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -845,6 +845,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread)); SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running); SEQ_printf(m, " .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running); + SEQ_printf(m, " .%-30s: %d\n", "h_nr_delayed", cfs_rq->h_nr_delayed); SEQ_printf(m, " .%-30s: %d\n", "idle_nr_running", cfs_rq->idle_nr_running); SEQ_printf(m, " .%-30s: %d\n", "idle_h_nr_running", diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9d7a2dd2c260..97ee48c8bf5e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5465,9 +5465,33 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); -static inline void finish_delayed_dequeue_entity(struct sched_entity *se) +static void set_delayed(struct sched_entity *se) +{ + se->sched_delayed = 1; + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + cfs_rq->h_nr_delayed++; + if (cfs_rq_throttled(cfs_rq)) + break; + } +} + +static void clear_delayed(struct sched_entity *se) { se->sched_delayed = 0; + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + cfs_rq->h_nr_delayed--; + if (cfs_rq_throttled(cfs_rq)) + break; + } +} + +static inline void finish_delayed_dequeue_entity(struct sched_entity *se) +{ + clear_delayed(se); if (sched_feat(DELAY_ZERO) && se->vlag > 0) se->vlag = 0; } @@ -5496,7 +5520,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (sched_feat(DELAY_DEQUEUE) && delay && !entity_eligible(cfs_rq, se)) { update_load_avg(cfs_rq, se, 0); - se->sched_delayed = 1; + set_delayed(se); return false; } } @@ -5908,7 +5932,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - long task_delta, idle_task_delta, dequeue = 1; + long task_delta, idle_task_delta, delayed_delta, dequeue = 1; long rq_h_nr_running = rq->cfs.h_nr_running; raw_spin_lock(&cfs_b->lock); @@ -5941,6 +5965,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) task_delta = cfs_rq->h_nr_running; idle_task_delta = cfs_rq->idle_h_nr_running; + delayed_delta = cfs_rq->h_nr_delayed; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); int flags; @@ -5964,6 +5989,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running -= task_delta; qcfs_rq->idle_h_nr_running -= idle_task_delta; + qcfs_rq->h_nr_delayed -= delayed_delta; if (qcfs_rq->load.weight) { /* Avoid re-evaluating load for this entity: */ @@ -5986,6 +6012,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running -= task_delta; qcfs_rq->idle_h_nr_running -= idle_task_delta; + qcfs_rq->h_nr_delayed -= delayed_delta; } /* At this point se is NULL and we are at root level*/ @@ -6011,7 +6038,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - long task_delta, idle_task_delta; + long task_delta, idle_task_delta, delayed_delta; long rq_h_nr_running = rq->cfs.h_nr_running; se = cfs_rq->tg->se[cpu_of(rq)]; @@ -6047,6 +6074,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) task_delta = cfs_rq->h_nr_running; idle_task_delta = cfs_rq->idle_h_nr_running; + delayed_delta = cfs_rq->h_nr_delayed; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); @@ -6064,6 +6092,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running += task_delta; qcfs_rq->idle_h_nr_running += idle_task_delta; + qcfs_rq->h_nr_delayed += delayed_delta; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6081,6 +6110,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running += task_delta; qcfs_rq->idle_h_nr_running += idle_task_delta; + qcfs_rq->h_nr_delayed += delayed_delta; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6934,7 +6964,7 @@ requeue_delayed_entity(struct sched_entity *se) } update_load_avg(cfs_rq, se, 0); - se->sched_delayed = 0; + clear_delayed(se); } /* @@ -6948,6 +6978,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; int idle_h_nr_running = task_has_idle_policy(p); + int h_nr_delayed = 0; int task_new = !(flags & ENQUEUE_WAKEUP); int rq_h_nr_running = rq->cfs.h_nr_running; u64 slice = 0; @@ -6974,6 +7005,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (p->in_iowait) cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT); + if (task_new) + h_nr_delayed = !!se->sched_delayed; + for_each_sched_entity(se) { if (se->on_rq) { if (se->sched_delayed) @@ -6996,6 +7030,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq->h_nr_running++; cfs_rq->idle_h_nr_running += idle_h_nr_running; + cfs_rq->h_nr_delayed += h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = 1; @@ -7019,6 +7054,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq->h_nr_running++; cfs_rq->idle_h_nr_running += idle_h_nr_running; + cfs_rq->h_nr_delayed += h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = 1; @@ -7081,6 +7117,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) struct task_struct *p = NULL; int idle_h_nr_running = 0; int h_nr_running = 0; + int h_nr_delayed = 0; struct cfs_rq *cfs_rq; u64 slice = 0; @@ -7088,6 +7125,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) p = task_of(se); h_nr_running = 1; idle_h_nr_running = task_has_idle_policy(p); + if (!task_sleep && !task_delayed) + h_nr_delayed = !!se->sched_delayed; } else { cfs_rq = group_cfs_rq(se); slice = cfs_rq_min_slice(cfs_rq); @@ -7105,6 +7144,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) cfs_rq->h_nr_running -= h_nr_running; cfs_rq->idle_h_nr_running -= idle_h_nr_running; + cfs_rq->h_nr_delayed -= h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = h_nr_running; @@ -7143,6 +7183,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) cfs_rq->h_nr_running -= h_nr_running; cfs_rq->idle_h_nr_running -= idle_h_nr_running; + cfs_rq->h_nr_delayed -= h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = h_nr_running; diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index fc07382361a8..fee75cc2c47b 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -321,7 +321,7 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq) { if (___update_load_sum(now, &cfs_rq->avg, scale_load_down(cfs_rq->load.weight), - cfs_rq->h_nr_running, + cfs_rq->h_nr_running - cfs_rq->h_nr_delayed, cfs_rq->curr != NULL)) { ___update_load_avg(&cfs_rq->avg, 1); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 76f5f53a645f..1e494af2cd23 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -649,6 +649,7 @@ struct cfs_rq { unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */ unsigned int idle_nr_running; /* SCHED_IDLE */ unsigned int idle_h_nr_running; /* SCHED_IDLE */ + unsigned int h_nr_delayed; s64 avg_vruntime; u64 avg_load; @@ -898,8 +899,11 @@ struct dl_rq { static inline void se_update_runnable(struct sched_entity *se) { - if (!entity_is_task(se)) - se->runnable_weight = se->my_q->h_nr_running; + if (!entity_is_task(se)) { + struct cfs_rq *cfs_rq = se->my_q; + + se->runnable_weight = cfs_rq->h_nr_running - cfs_rq->h_nr_delayed; + } } static inline long se_runnable(struct sched_entity *se) -- cgit v1.2.3 From c7f7e9c73178e0e342486fd31e7f363ef60e3f83 Mon Sep 17 00:00:00 2001 From: "Vineeth Pillai (Google)" Date: Thu, 12 Dec 2024 22:22:37 -0500 Subject: sched/dlserver: Fix dlserver time accounting dlserver time is accounted when: - dlserver is active and the dlserver proxies the cfs task. - dlserver is active but deferred and cfs task runs after being picked through the normal fair class pick. dl_server_update is called in two places to make sure that both the above times are accounted for. But it doesn't check if dlserver is active or not. Now that we have this dl_server_active flag, we can consolidate dl_server_update into one place and all we need to check is whether dlserver is active or not. When dlserver is active there is only two possible conditions: - dlserver is deferred. - cfs task is running on behalf of dlserver. Fixes: a110a81c52a9 ("sched/deadline: Deferrable dl server") Signed-off-by: "Vineeth Pillai (Google)" Signed-off-by: Peter Zijlstra (Intel) Tested-by: Marcel Ziswiler # ROCK 5B Link: https://lore.kernel.org/r/20241213032244.877029-2-vineeth@bitbyteword.org --- kernel/sched/fair.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'kernel/sched/fair.c') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 97ee48c8bf5e..53a4f78b8340 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1159,8 +1159,6 @@ static inline void update_curr_task(struct task_struct *p, s64 delta_exec) trace_sched_stat_runtime(p, delta_exec); account_group_exec_runtime(p, delta_exec); cgroup_account_cputime(p, delta_exec); - if (p->dl_server) - dl_server_update(p->dl_server, delta_exec); } static inline bool did_preempt_short(struct cfs_rq *cfs_rq, struct sched_entity *curr) @@ -1237,11 +1235,16 @@ static void update_curr(struct cfs_rq *cfs_rq) update_curr_task(p, delta_exec); /* - * Any fair task that runs outside of fair_server should - * account against fair_server such that it can account for - * this time and possibly avoid running this period. + * If the fair_server is active, we need to account for the + * fair_server time whether or not the task is running on + * behalf of fair_server or not: + * - If the task is running on behalf of fair_server, we need + * to limit its time based on the assigned runtime. + * - Fair task that runs outside of fair_server should account + * against fair_server such that it can account for this time + * and possibly avoid running this period. */ - if (p->dl_server != &rq->fair_server) + if (dl_server_active(&rq->fair_server)) dl_server_update(&rq->fair_server, delta_exec); } -- cgit v1.2.3