Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
Merge tag 'sched-urgent-2026-05-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fixes from Ingo Molnar:
- Fix the delayed dequeue negative lag increase fix in the
fair scheduler (Peter Zijlstra)
- Fix wakeup_preempt_fair() to do proper delayed dequeue
(Vincent Guittot)
- Clear sched_entity::rel_deadline when initializing
forked entities, which bug can cause all tasks to be
EEVDF-ineligible, causing a NULL pointer dereference
crash in pick_next_entity() (Zicheng Qu)
* tag 'sched-urgent-2026-05-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/fair: Clear rel_deadline when initializing forked entities
sched/fair: Fix wakeup_preempt_fair() vs delayed dequeue
sched/fair: Fix the negative lag increase fix
+26
-19
+1
kernel/sched/core.c
+1
kernel/sched/core.c
+25
-19
kernel/sched/fair.c
+25
-19
kernel/sched/fair.c
···
847
847
* Similarly, check that the entity didn't gain positive lag when DELAY_ZERO
848
848
* is set.
849
849
*
850
-
* Return true if the lag has been adjusted.
850
+
* Return true if the vlag has been modified. Specifically:
851
+
*
852
+
* se->vlag != avg_vruntime() - se->vruntime
853
+
*
854
+
* This can be due to clamping in entity_lag() or clamping due to
855
+
* sched_delayed. Either way, when vlag is modified and the entity is
856
+
* retained, the tree needs to be adjusted.
851
857
*/
852
858
static __always_inline
853
859
bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
854
860
{
855
-
s64 vlag = entity_lag(cfs_rq, se, avg_vruntime(cfs_rq));
856
-
bool ret;
861
+
u64 avruntime = avg_vruntime(cfs_rq);
862
+
s64 vlag = entity_lag(cfs_rq, se, avruntime);
857
863
858
864
WARN_ON_ONCE(!se->on_rq);
859
865
···
869
863
if (sched_feat(DELAY_ZERO))
870
864
vlag = min(vlag, 0);
871
865
}
872
-
ret = (vlag == se->vlag);
873
866
se->vlag = vlag;
874
867
875
-
return ret;
868
+
return avruntime - vlag != se->vruntime;
876
869
}
877
870
878
871
/*
···
1104
1099
*
1105
1100
* Which allows tree pruning through eligibility.
1106
1101
*/
1107
-
static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq, bool protect)
1102
+
static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq, bool protect)
1108
1103
{
1109
1104
struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
1110
1105
struct sched_entity *se = __pick_first_entity(cfs_rq);
···
1173
1168
best = curr;
1174
1169
1175
1170
return best;
1176
-
}
1177
-
1178
-
static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
1179
-
{
1180
-
return __pick_eevdf(cfs_rq, true);
1181
1171
}
1182
1172
1183
1173
struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
···
5749
5749
* 4) do not run the "skip" process, if something else is available
5750
5750
*/
5751
5751
static struct sched_entity *
5752
-
pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
5752
+
pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq, bool protect)
5753
5753
{
5754
5754
struct sched_entity *se;
5755
5755
5756
-
se = pick_eevdf(cfs_rq);
5756
+
se = pick_eevdf(cfs_rq, protect);
5757
5757
if (se->sched_delayed) {
5758
5758
dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
5759
5759
/*
···
9027
9027
{
9028
9028
enum preempt_wakeup_action preempt_action = PREEMPT_WAKEUP_PICK;
9029
9029
struct task_struct *donor = rq->donor;
9030
-
struct sched_entity *se = &donor->se, *pse = &p->se;
9030
+
struct sched_entity *nse, *se = &donor->se, *pse = &p->se;
9031
9031
struct cfs_rq *cfs_rq = task_cfs_rq(donor);
9032
9032
int cse_is_idle, pse_is_idle;
9033
9033
···
9138
9138
}
9139
9139
9140
9140
pick:
9141
-
/*
9142
-
* If @p has become the most eligible task, force preemption.
9143
-
*/
9144
-
if (__pick_eevdf(cfs_rq, preempt_action != PREEMPT_WAKEUP_SHORT) == pse)
9141
+
nse = pick_next_entity(rq, cfs_rq, preempt_action != PREEMPT_WAKEUP_SHORT);
9142
+
/* If @p has become the most eligible task, force preemption */
9143
+
if (nse == pse)
9145
9144
goto preempt;
9145
+
9146
+
/*
9147
+
* Because p is enqueued, nse being null can only mean that we
9148
+
* dequeued a delayed task.
9149
+
*/
9150
+
if (!nse)
9151
+
goto pick;
9146
9152
9147
9153
if (sched_feat(RUN_TO_PARITY))
9148
9154
update_protect_slice(cfs_rq, se);
···
9185
9179
9186
9180
throttled |= check_cfs_rq_runtime(cfs_rq);
9187
9181
9188
-
se = pick_next_entity(rq, cfs_rq);
9182
+
se = pick_next_entity(rq, cfs_rq, true);
9189
9183
if (!se)
9190
9184
goto again;
9191
9185
cfs_rq = group_cfs_rq(se);