summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-03-26 09:18:30 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2023-03-26 09:18:30 -0700
commit18940c888c85fd7527375343bd4fcc94a540c69c (patch)
tree72a803638790e8e44d44f3774579aee7aa6b7a53 /kernel
parent974fc94336df81137b3b3502e73f89282a743607 (diff)
parenta53ce18cacb477dd0513c607f187d16f0fa96f71 (diff)
Merge tag 'sched_urgent_for_v6.3_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fix from Borislav Petkov: - Fix a corner case where vruntime of a task is not being sanitized * tag 'sched_urgent_for_v6.3_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: sched/fair: Sanitize vruntime of entity being migrated
Diffstat (limited to 'kernel')
-rw-r--r--kernel/sched/core.c3
-rw-r--r--kernel/sched/fair.c55
2 files changed, 47 insertions, 11 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 488655f2319f..0d18c3969f90 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2084,6 +2084,9 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
void activate_task(struct rq *rq, struct task_struct *p, int flags)
{
+ if (task_on_rq_migrating(p))
+ flags |= ENQUEUE_MIGRATED;
+
enqueue_task(rq, p, flags);
p->on_rq = TASK_ON_RQ_QUEUED;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7a1b1f855b96..6986ea31c984 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4648,11 +4648,33 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
#endif
}
+static inline bool entity_is_long_sleeper(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq;
+ u64 sleep_time;
+
+ if (se->exec_start == 0)
+ return false;
+
+ cfs_rq = cfs_rq_of(se);
+
+ sleep_time = rq_clock_task(rq_of(cfs_rq));
+
+ /* Happen while migrating because of clock task divergence */
+ if (sleep_time <= se->exec_start)
+ return false;
+
+ sleep_time -= se->exec_start;
+ if (sleep_time > ((1ULL << 63) / scale_load_down(NICE_0_LOAD)))
+ return true;
+
+ return false;
+}
+
static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
{
u64 vruntime = cfs_rq->min_vruntime;
- u64 sleep_time;
/*
* The 'current' period is already promised to the current tasks,
@@ -4684,13 +4706,24 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
/*
* Pull vruntime of the entity being placed to the base level of
- * cfs_rq, to prevent boosting it if placed backwards. If the entity
- * slept for a long time, don't even try to compare its vruntime with
- * the base as it may be too far off and the comparison may get
- * inversed due to s64 overflow.
- */
- sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start;
- if ((s64)sleep_time > 60LL * NSEC_PER_SEC)
+ * cfs_rq, to prevent boosting it if placed backwards.
+ * However, min_vruntime can advance much faster than real time, with
+ * the extreme being when an entity with the minimal weight always runs
+ * on the cfs_rq. If the waking entity slept for a long time, its
+ * vruntime difference from min_vruntime may overflow s64 and their
+ * comparison may get inversed, so ignore the entity's original
+ * vruntime in that case.
+ * The maximal vruntime speedup is given by the ratio of normal to
+ * minimal weight: scale_load_down(NICE_0_LOAD) / MIN_SHARES.
+ * When placing a migrated waking entity, its exec_start has been set
+ * from a different rq. In order to take into account a possible
+ * divergence between new and prev rq's clocks task because of irq and
+ * stolen time, we take an additional margin.
+ * So, cutting off on the sleep time of
+ * 2^63 / scale_load_down(NICE_0_LOAD) ~ 104 days
+ * should be safe.
+ */
+ if (entity_is_long_sleeper(se))
se->vruntime = vruntime;
else
se->vruntime = max_vruntime(se->vruntime, vruntime);
@@ -4770,6 +4803,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
if (flags & ENQUEUE_WAKEUP)
place_entity(cfs_rq, se, 0);
+ /* Entity has migrated, no longer consider this task hot */
+ if (flags & ENQUEUE_MIGRATED)
+ se->exec_start = 0;
check_schedstat_required();
update_stats_enqueue_fair(cfs_rq, se, flags);
@@ -7657,9 +7693,6 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
/* Tell new CPU we are migrated */
se->avg.last_update_time = 0;
- /* We have migrated, no longer consider this task hot */
- se->exec_start = 0;
-
update_scan_period(p, new_cpu);
}