From 32fe5c4c3e553ae83f6c45242b50c79cfd74cd5a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 20 Dec 2024 06:32:19 +0000 Subject: [PATCH] sched/fair: Fix value reported by hot tasks pulled in /proc/schedstat [ Upstream commit a430d99e349026d53e2557b7b22bd2ebd61fe12a ] In /proc/schedstat, lb_hot_gained reports the number hot tasks pulled during load balance. This value is incremented in can_migrate_task() if the task is migratable and hot. After incrementing the value, load balancer can still decide not to migrate this task leading to wrong accounting. Fix this by incrementing stats when hot tasks are detached. This issue only exists in detach_tasks() where we can decide to not migrate hot task even if it is migratable. However, in detach_one_task(), we migrate it unconditionally. [Swapnil: Handled the case where nr_failed_migrations_hot was not accounted properly and wrote commit log] Fixes: d31980846f96 ("sched: Move up affinity check to mitigate useless redoing overhead") Signed-off-by: Peter Zijlstra (Intel) Reported-by: "Gautham R. Shenoy" Not-yet-signed-off-by: Peter Zijlstra Signed-off-by: Swapnil Sapkal Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20241220063224.17767-2-swapnil.sapkal@amd.com Signed-off-by: Sasha Levin --- include/linux/sched.h | 1 + kernel/sched/fair.c | 17 +++++++++++++---- 2 files changed, 14 insertions(+), 4 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index d4f9d82c69e0..2af0a8859d64 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -896,6 +896,7 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned sched_task_hot:1; /* Force alignment to the next boundary: */ unsigned :0; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3b2cfdb8d788..cd9b411706b5 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8921,6 +8921,8 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) int tsk_cache_hot; lockdep_assert_rq_held(env->src_rq); + if (p->sched_task_hot) + p->sched_task_hot = 0; /* * We do not migrate tasks that are: @@ -8993,10 +8995,8 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (tsk_cache_hot <= 0 || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { - if (tsk_cache_hot == 1) { - schedstat_inc(env->sd->lb_hot_gained[env->idle]); - schedstat_inc(p->stats.nr_forced_migrations); - } + if (tsk_cache_hot == 1) + p->sched_task_hot = 1; return 1; } @@ -9011,6 +9011,12 @@ static void detach_task(struct task_struct *p, struct lb_env *env) { lockdep_assert_rq_held(env->src_rq); + if (p->sched_task_hot) { + p->sched_task_hot = 0; + schedstat_inc(env->sd->lb_hot_gained[env->idle]); + schedstat_inc(p->stats.nr_forced_migrations); + } + deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK); set_task_cpu(p, env->dst_cpu); } @@ -9171,6 +9177,9 @@ static int detach_tasks(struct lb_env *env) continue; next: + if (p->sched_task_hot) + schedstat_inc(p->stats.nr_failed_migrations_hot); + list_move(&p->se.group_node, tasks); }