summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2026-09-30 07:58:15 -1000
committerTejun Heo <tj@kernel.org>2026-09-30 07:58:15 -1000
commit972cf7de2cbe127d3e55cf0a413c78754fa6a8e4 (patch)
treea027c7ef30cbbe86a80e929f56370808e1413d3b /kernel
parentf2f095c87603b8dfb6752e130d902970371c3852 (diff)
parentcc07fae1de5dbf514a9a3978050ee3cf5fe20d3c (diff)
sched_ext: Merge branch 'for-7.3-fixes' into for-7.4
Pull to receive cc07fae1de5d ("selftests/sched_ext: Add a test for ops.dequeue() on remote local DSQ moves") and resolve its conflict with f73ec6791424 ("sched_ext: Add selftest for blocked donor admission") here so that for-next merges clean. Conflicts: kept both auto-test-targets entries in the selftests Makefile, where each side added one after dequeue_iter. Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/sched/ext/ext.c32
-rw-r--r--kernel/sched/ext/inlines.h8
-rw-r--r--kernel/sched/ext/sub.c4
-rw-r--r--kernel/sched/sched.h5
4 files changed, 37 insertions, 12 deletions
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 405d0d1038f8..0ef48c2ba6c8 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -2295,8 +2295,8 @@ static void set_task_runnable(struct rq *rq, struct task_struct *p)
}
/*
- * list_add_tail() must be used. scx_bypass() depends on tasks being
- * appended to the runnable_list.
+ * list_add_tail() must be used. scx_bypass() and rq_offline_scx()
+ * depend on tasks being appended to the runnable_list.
*/
list_add_tail(&p->scx.runnable_node, &rq->scx.runnable_list);
@@ -2325,6 +2325,13 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_
u64 enq_flags = core_enq_flags | rq->scx.remote_activate_enq_flags;
/*
+ * An SCX-internal migration ends on arrival. Clear sticky_cpu so @p can
+ * leave custody when inserted into the destination DSQ.
+ */
+ if (sticky_cpu >= 0)
+ p->scx.sticky_cpu = -1;
+
+ /*
* SCX_RQ_IN_WAKEUP promises a task_woken_scx() call once this enqueue
* returns. Only the core's wakeup path delivers one. The flags stashed
* for a remote activation may carry the wakeup bit without it.
@@ -2363,9 +2370,6 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_
dl_server_start(&rq->ext_server);
scx_do_enqueue_task(rq, p, enq_flags, sticky_cpu);
-
- if (sticky_cpu >= 0)
- p->scx.sticky_cpu = -1;
out:
rq->scx.flags &= ~SCX_RQ_IN_WAKEUP;
@@ -4098,8 +4102,26 @@ static void rq_online_scx(struct rq *rq)
static void rq_offline_scx(struct rq *rq)
{
+ struct task_struct *p, *n;
+
rq->scx.flags &= ~SCX_RQ_ONLINE;
+
+ /* sched domain rebuilds call rq_offline with the CPU staying alive */
+ if (cpu_active(cpu_of(rq)))
+ return;
+
scx_rescue_flush(rq);
+
+ /*
+ * An offline CPU no longer calls ops.dispatch(). Re-enqueue its tasks
+ * onto the local DSQ so that they run here and balance_push() moves
+ * them off.
+ */
+ list_for_each_entry_safe_reverse(p, n, &rq->scx.runnable_list, scx.runnable_node) {
+ if (p->scx.dsq == &rq->scx.local_dsq)
+ continue;
+ guard(sched_change)(p, DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK);
+ }
}
static bool check_rq_for_timeouts(struct rq *rq)
diff --git a/kernel/sched/ext/inlines.h b/kernel/sched/ext/inlines.h
index 2ff5479334cb..8de9d8fb4b25 100644
--- a/kernel/sched/ext/inlines.h
+++ b/kernel/sched/ext/inlines.h
@@ -70,7 +70,13 @@ scx_dispatch_sched(struct scx_sched *sch, struct rq *rq,
#endif /* CONFIG_EXT_SUB_SCHED */
}
- if (unlikely(!SCX_HAS_OP(sch, dispatch)) || !scx_rq_online(rq))
+ /*
+ * scx_rq_online() can't be used. Its cpu_active() test goes false
+ * before CPU hotplug waits for an RCU grace period, and
+ * rq_offline_scx() moves this CPU's tasks to the local DSQ only after
+ * the wait. The grace period can depend on those tasks running.
+ */
+ if (unlikely(!SCX_HAS_OP(sch, dispatch)) || !(rq->scx.flags & SCX_RQ_ONLINE))
return SCX_DSP_NONE;
dspc->rq = rq;
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index 9af09807951d..48e17aeb1cb6 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -586,10 +586,6 @@ void scx_rescue_flush(struct rq *rq)
lockdep_assert_rq_held(rq);
- /* sched domain rebuilds call rq_offline with the CPU staying alive */
- if (cpu_active(cpu_of(rq)))
- return;
-
/* end the current rescue */
if (rq->scx.rescue.curr)
scx_task_slice_ended(rq, rq->scx.rescue.curr);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 64a4ccc6e0d0..0a34f0da1ec3 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -4274,8 +4274,9 @@ extern void balance_callbacks(struct rq *rq, struct balance_callback *head);
* after which it is enqueued again.
*
* Typically this must be called while holding task_rq_lock, since most/all
- * properties are serialized under those locks. There is currently one
- * exception to this rule in sched/ext which only holds rq->lock.
+ * properties are serialized under those locks. There are currently two
+ * exceptions to this rule in sched/ext which only hold rq->lock: scx_bypass()
+ * and rq_offline_scx().
*/
/*