sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted

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

1 files changed, 60 insertions, 0 deletions

diff --git a/mm/init-mm.c b/mm/init-mm.c
new file mode 100644
index 000000000..3e792aad7
--- /dev/null
+++ b/mm/init-mm.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/mm_types.h>
+#include <linux/maple_tree.h>
+#include <linux/rwsem.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/cpumask.h>
+#include <linux/mman.h>
+#include <linux/pgtable.h>
+
+#include <linux/atomic.h>
+#include <linux/user_namespace.h>
+#include <linux/iommu.h>
+#include <asm/mmu.h>
+
+#ifndef INIT_MM_CONTEXT
+#define INIT_MM_CONTEXT(name)
+#endif
+
+const struct vm_operations_struct vma_dummy_vm_ops;
+
+/*
+ * For dynamically allocated mm_structs, there is a dynamically sized cpumask
+ * at the end of the structure, the size of which depends on the maximum CPU
+ * number the system can see. That way we allocate only as much memory for
+ * mm_cpumask() as needed for the hundreds, or thousands of processes that
+ * a system typically runs.
+ *
+ * Since there is only one init_mm in the entire system, keep it simple
+ * and size this cpu_bitmask to NR_CPUS.
+ */
+struct mm_struct init_mm = {
+	.mm_mt		= MTREE_INIT_EXT(mm_mt, MM_MT_FLAGS, init_mm.mmap_lock),
+	.pgd		= swapper_pg_dir,
+	.mm_users	= ATOMIC_INIT(2),
+	.mm_count	= ATOMIC_INIT(1),
+	.write_protect_seq = SEQCNT_ZERO(init_mm.write_protect_seq),
+	MMAP_LOCK_INITIALIZER(init_mm)
+	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
+	.arg_lock	=  __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
+	.mmlist		= LIST_HEAD_INIT(init_mm.mmlist),
+#ifdef CONFIG_PER_VMA_LOCK
+	.vma_writer_wait = __RCUWAIT_INITIALIZER(init_mm.vma_writer_wait),
+	.mm_lock_seq	= SEQCNT_ZERO(init_mm.mm_lock_seq),
+#endif
+#ifdef CONFIG_SCHED_MM_CID
+	.mm_cid.lock = __RAW_SPIN_LOCK_UNLOCKED(init_mm.mm_cid.lock),
+#endif
+	.flexible_array	= MM_STRUCT_FLEXIBLE_ARRAY_INIT,
+	INIT_MM_CONTEXT(init_mm)
+};
+
+void setup_initial_init_mm(void *start_code, void *end_code,
+			   void *end_data, void *brk)
+{
+	init_mm.start_code = (unsigned long)start_code;
+	init_mm.end_code = (unsigned long)end_code;
+	init_mm.end_data = (unsigned long)end_data;
+	init_mm.brk = (unsigned long)brk;
+}