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) <peterz@infradead.org>
Reported-by: "Gautham R. Shenoy" <gautham.shenoy@amd.com>
Not-yet-signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241220063224.17767-2-swapnil.sapkal@amd.com
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 875f3d317b9c897ae62a9950d71d8f3ee73a3e05..5d0a44e4db4b5d2e8aaf4f53f21b0054a6b3874f 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -874,6 +874,7 @@ 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 4056330d38887fc50c25d10829b562dbe81c34f2..20044e7506ae1756977842411691ab17cdf82d70 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8022,6 +8022,8 @@ 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:
@@ -8094,10 +8096,8 @@ 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;
        }
 
@@ -8112,6 +8112,12 @@ 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);
 }
@@ -8274,6 +8280,9 @@ 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);
        }