sched: Add logic to zap balance callbacks if we pick again

With proxy-exec, a task is selected to run via pick_next_task(),
and then if it is a mutex blocked task, we call find_proxy_task()
to find a runnable owner. If the runnable owner is on another
cpu, we will need to migrate the selected donor task away, after
which we will pick_again can call pick_next_task() to choose
something else.

However, in the first call to pick_next_task(), we may have
had a balance_callback setup by the class scheduler. After we
pick again, its possible pick_next_task_fair() will be called
which calls sched_balance_newidle() and sched_balance_rq().

This will throw a warning:
[    8.796467] rq->balance_callback && rq->balance_callback != &balance_push_callback
[    8.796467] WARNING: CPU: 32 PID: 458 at kernel/sched/sched.h:1750 sched_balance_rq+0xe92/0x1250
...
[    8.796467] Call Trace:
[    8.796467]  <TASK>
[    8.796467]  ? __warn.cold+0xb2/0x14e
[    8.796467]  ? sched_balance_rq+0xe92/0x1250
[    8.796467]  ? report_bug+0x107/0x1a0
[    8.796467]  ? handle_bug+0x54/0x90
[    8.796467]  ? exc_invalid_op+0x17/0x70
[    8.796467]  ? asm_exc_invalid_op+0x1a/0x20
[    8.796467]  ? sched_balance_rq+0xe92/0x1250
[    8.796467]  sched_balance_newidle+0x295/0x820
[    8.796467]  pick_next_task_fair+0x51/0x3f0
[    8.796467]  __schedule+0x23a/0x14b0
[    8.796467]  ? lock_release+0x16d/0x2e0
[    8.796467]  schedule+0x3d/0x150
[    8.796467]  worker_thread+0xb5/0x350
[    8.796467]  ? __pfx_worker_thread+0x10/0x10
[    8.796467]  kthread+0xee/0x120
[    8.796467]  ? __pfx_kthread+0x10/0x10
[    8.796467]  ret_from_fork+0x31/0x50
[    8.796467]  ? __pfx_kthread+0x10/0x10
[    8.796467]  ret_from_fork_asm+0x1a/0x30
[    8.796467]  </TASK>

This is because if a RT task was originally picked, it will
setup the rq->balance_callback with push_rt_tasks() via
set_next_task_rt().

Once the task is migrated away and we pick again, we haven't
processed any balance callbacks, so rq->balance_callback is not
in the same state as it was the first time pick_next_task was
called.

To handle this, add a zap_balance_callbacks() helper function
which cleans up the balance callbacks without running them. This
should be ok, as we are effectively undoing the state set in
the first call to pick_next_task(), and when we pick again,
the new callback can be configured for the donor task actually
selected.

Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://patch.msgid.link/20260324191337.1841376-9-jstultz@google.com

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index acb5894e7714eb63f98a735df19dde36021135f5..162b24c76077e4419176f82bf5e2787d1bd5fae9 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4917,6 +4917,34 @@ static inline void finish_task(struct task_struct *prev)
        smp_store_release(&prev->on_cpu, 0);
 }
 
+/*
+ * Only called from __schedule context
+ *
+ * There are some cases where we are going to re-do the action
+ * that added the balance callbacks. We may not be in a state
+ * where we can run them, so just zap them so they can be
+ * properly re-added on the next time around. This is similar
+ * handling to running the callbacks, except we just don't call
+ * them.
+ */
+static void zap_balance_callbacks(struct rq *rq)
+{
+       struct balance_callback *next, *head;
+       bool found = false;
+
+       lockdep_assert_rq_held(rq);
+
+       head = rq->balance_callback;
+       while (head) {
+               if (head == &balance_push_callback)
+                       found = true;
+               next = head->next;
+               head->next = NULL;
+               head = next;
+       }
+       rq->balance_callback = found ? &balance_push_callback : NULL;
+}
+
 static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
 {
        void (*func)(struct rq *rq);
@@ -6862,10 +6890,14 @@ pick_again:
                rq_set_donor(rq, next);
                if (unlikely(next->blocked_on)) {
                        next = find_proxy_task(rq, next, &rf);
-                       if (!next)
+                       if (!next) {
+                               zap_balance_callbacks(rq);
                                goto pick_again;
-                       if (next == rq->idle)
+                       }
+                       if (next == rq->idle) {
+                               zap_balance_callbacks(rq);
                                goto keep_resched;
+                       }
                }
                if (rq->donor == prev_donor && prev != next) {
                        struct task_struct *donor = rq->donor;