sched/fair: set_load_weight() must also call reweight_task() for SCHED_IDLE tasks

When a task's weight is being changed, set_load_weight() is called with
@update_load set. As weight changes aren't trivial for the fair class,
set_load_weight() calls fair.c::reweight_task() for fair class tasks.

However, set_load_weight() first tests task_has_idle_policy() on entry and
skips calling reweight_task() for SCHED_IDLE tasks. This is buggy as
SCHED_IDLE tasks are just fair tasks with a very low weight and they would
incorrectly skip load, vlag and position updates.

Fix it by updating reweight_task() to take struct load_weight as idle weight
can't be expressed with prio and making set_load_weight() call
reweight_task() for SCHED_IDLE tasks too when @update_load is set.

Fixes: 9059393e4ec1 ("sched/fair: Use reweight_entity() for set_user_nice()")
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org # v4.15+
Link: http://lkml.kernel.org/r/20240624102331.GI31592@noisy.programming.kicks-ass.net

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0935f9d4bb7be085bdc8377f8bd919c70a044694..747683487be7e0687345c7db000821693cbcafcd 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1328,27 +1328,24 @@ int tg_nop(struct task_group *tg, void *data)
 void set_load_weight(struct task_struct *p, bool update_load)
 {
        int prio = p->static_prio - MAX_RT_PRIO;
-       struct load_weight *load = &p->se.load;
+       struct load_weight lw;
 
-       /*
-        * SCHED_IDLE tasks get minimal weight:
-        */
        if (task_has_idle_policy(p)) {
-               load->weight = scale_load(WEIGHT_IDLEPRIO);
-               load->inv_weight = WMULT_IDLEPRIO;
-               return;
+               lw.weight = scale_load(WEIGHT_IDLEPRIO);
+               lw.inv_weight = WMULT_IDLEPRIO;
+       } else {
+               lw.weight = scale_load(sched_prio_to_weight[prio]);
+               lw.inv_weight = sched_prio_to_wmult[prio];
        }
 
        /*
         * SCHED_OTHER tasks have to update their load when changing their
         * weight
         */
-       if (update_load && p->sched_class == &fair_sched_class) {
-               reweight_task(p, prio);
-       } else {
-               load->weight = scale_load(sched_prio_to_weight[prio]);
-               load->inv_weight = sched_prio_to_wmult[prio];
-       }
+       if (update_load && p->sched_class == &fair_sched_class)
+               reweight_task(p, &lw);
+       else
+               p->se.load = lw;
 }
 
 #ifdef CONFIG_UCLAMP_TASK

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 41b58387023d5aee15c346e1db9faa7ae7852319..f205e2482690da7aa02504023c4ba29427b0d0b3 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3835,15 +3835,14 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
        }
 }
 
-void reweight_task(struct task_struct *p, int prio)
+void reweight_task(struct task_struct *p, const struct load_weight *lw)
 {
        struct sched_entity *se = &p->se;
        struct cfs_rq *cfs_rq = cfs_rq_of(se);
        struct load_weight *load = &se->load;
-       unsigned long weight = scale_load(sched_prio_to_weight[prio]);
 
-       reweight_entity(cfs_rq, se, weight);
-       load->inv_weight = sched_prio_to_wmult[prio];
+       reweight_entity(cfs_rq, se, lw->weight);
+       load->inv_weight = lw->inv_weight;
 }
 
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 62fd8bc6fd08add8c0f61133d697d9b1d313b9d8..9ab53435debd58f400404cf06eb5e32a58d15110 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2509,7 +2509,7 @@ extern void init_sched_dl_class(void);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
 
-extern void reweight_task(struct task_struct *p, int prio);
+extern void reweight_task(struct task_struct *p, const struct load_weight *lw);
 
 extern void resched_curr(struct rq *rq);
 extern void resched_cpu(int cpu);