From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001
From: Tim Chen <tim.c.chen@linux.intel.com>
Date: Mon, 21 Sep 2026 17:37:22 -0700
Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix
 LLC mis-scheduling bug

alb_break_llc() decides whether to break LLC preference during active
load balance. It does so by testing that every runnable fair task on the
source rq prefers its LLC:

	env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable

But the two counters cover different sets. nr_pref_llc_running is updated
in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued,
so it follows queued tasks. h_nr_runnable is updated in set_delayed()/
clear_delayed() and drops delay-dequeued tasks.

So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted
in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks,
alb_break_llc() returns false, and active balance is free to pull a task
off its preferred LLC. Active balance only moves runnable tasks, and this
is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB
skips the per-task test in can_migrate_task(). The runnable set is the one
we want.

Fix it on the counter side. A task should be counted in
nr_pref_llc_running exactly while it is both queued on its preferred LLC
(pref_llc_queued) and runnable (!sched_delayed). Define that membership
once in task_pref_llc_runnable(), and adjust the counter only through
pref_llc_running_inc()/pref_llc_running_dec() from the four sites that
change either input: account_llc_enqueue(), account_llc_dequeue(),
set_delayed() and clear_delayed(). Gating every update on the same
predicate keeps the delay, wake and dequeue paths from double-counting
or underflowing; see the comments at those sites for the ordering.

nr_llc_running and sd->llc_counts are not touched and stay on queued
semantics.

Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC")
Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/
Reported-by: Zhan Xusheng <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com
---
 rust/syn/drops.rs | 60 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)
 create mode 100644 rust/syn/drops.rs

(limited to 'rust/syn/drops.rs')

diff --git a/rust/syn/drops.rs b/rust/syn/drops.rs
new file mode 100644
index 000000000..2c4ae333d
--- /dev/null
+++ b/rust/syn/drops.rs
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+use std::iter;
+use std::mem::ManuallyDrop;
+use std::ops::{Deref, DerefMut};
+use std::option;
+use std::slice;
+
+#[repr(transparent)]
+pub(crate) struct NoDrop<T: ?Sized>(ManuallyDrop<T>);
+
+impl<T> NoDrop<T> {
+    pub(crate) fn new(value: T) -> Self
+    where
+        T: TrivialDrop,
+    {
+        NoDrop(ManuallyDrop::new(value))
+    }
+}
+
+impl<T: ?Sized> Deref for NoDrop<T> {
+    type Target = T;
+    fn deref(&self) -> &Self::Target {
+        &self.0
+    }
+}
+
+impl<T: ?Sized> DerefMut for NoDrop<T> {
+    fn deref_mut(&mut self) -> &mut Self::Target {
+        &mut self.0
+    }
+}
+
+pub(crate) trait TrivialDrop {}
+
+impl<T> TrivialDrop for iter::Empty<T> {}
+impl<T> TrivialDrop for slice::Iter<'_, T> {}
+impl<T> TrivialDrop for slice::IterMut<'_, T> {}
+impl<T> TrivialDrop for option::IntoIter<&T> {}
+impl<T> TrivialDrop for option::IntoIter<&mut T> {}
+
+#[test]
+fn test_needs_drop() {
+    use std::mem::needs_drop;
+
+    struct NeedsDrop;
+
+    impl Drop for NeedsDrop {
+        fn drop(&mut self) {}
+    }
+
+    assert!(needs_drop::<NeedsDrop>());
+
+    // Test each of the types with a handwritten TrivialDrop impl above.
+    assert!(!needs_drop::<iter::Empty<NeedsDrop>>());
+    assert!(!needs_drop::<slice::Iter<NeedsDrop>>());
+    assert!(!needs_drop::<slice::IterMut<NeedsDrop>>());
+    assert!(!needs_drop::<option::IntoIter<&NeedsDrop>>());
+    assert!(!needs_drop::<option::IntoIter<&mut NeedsDrop>>());
+}
-- 
cgit v1.3.1