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, 46 insertions, 0 deletions

diff --git a/include/hyperv/hvgdk_ext.h b/include/hyperv/hvgdk_ext.h
new file mode 100644
index 000000000..641b591ee
--- /dev/null
+++ b/include/hyperv/hvgdk_ext.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Type definitions for the Microsoft Hypervisor.
+ */
+#ifndef _HV_HVGDK_EXT_H
+#define _HV_HVGDK_EXT_H
+
+#include "hvgdk_mini.h"
+
+/* Extended hypercalls */
+#define HV_EXT_CALL_QUERY_CAPABILITIES		0x8001
+#define HV_EXT_CALL_MEMORY_HEAT_HINT		0x8003
+
+/* Extended hypercalls */
+enum {		/* HV_EXT_CALL */
+	HV_EXTCALL_QUERY_CAPABILITIES = 0x8001,
+	HV_EXTCALL_MEMORY_HEAT_HINT   = 0x8003,
+};
+
+/* HV_EXT_OUTPUT_QUERY_CAPABILITIES */
+#define HV_EXT_CAPABILITY_MEMORY_COLD_DISCARD_HINT BIT(8)
+
+enum {		/* HV_EXT_MEMORY_HEAT_HINT_TYPE */
+	HV_EXTMEM_HEAT_HINT_COLD = 0,
+	HV_EXTMEM_HEAT_HINT_HOT = 1,
+	HV_EXTMEM_HEAT_HINT_COLD_DISCARD = 2,
+	HV_EXTMEM_HEAT_HINT_MAX
+};
+
+/*
+ * The whole argument should fit in a page to be able to pass to the hypervisor
+ * in one hypercall.
+ */
+#define HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES  \
+	((HV_HYP_PAGE_SIZE - sizeof(struct hv_memory_hint)) / \
+		sizeof(union hv_gpa_page_range))
+
+/* HvExtCallMemoryHeatHint hypercall */
+#define HV_EXT_MEMORY_HEAT_HINT_TYPE_COLD_DISCARD	2
+struct hv_memory_hint {		/* HV_EXT_INPUT_MEMORY_HEAT_HINT */
+	u64 heat_type : 2;	/* HV_EXTMEM_HEAT_HINT_* */
+	u64 reserved : 62;
+	union hv_gpa_page_range ranges[];
+} __packed;
+
+#endif /* _HV_HVGDK_EXT_H */