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, 114 insertions, 0 deletions

diff --git a/include/trace/perf.h b/include/trace/perf.h
new file mode 100644
index 000000000..348ad1d9b
--- /dev/null
+++ b/include/trace/perf.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#undef TRACE_SYSTEM_VAR
+
+#ifdef CONFIG_PERF_EVENTS
+
+#include "stages/stage6_event_callback.h"
+
+#undef __perf_count
+#define __perf_count(c)	(__count = (c))
+
+#undef __perf_task
+#define __perf_task(t)	(__task = (t))
+
+#undef __DECLARE_EVENT_CLASS
+#define __DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
+static notrace void							\
+do_perf_trace_##call(void *__data, proto)				\
+{									\
+	struct trace_event_call *event_call = __data;			\
+	struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\
+	struct trace_event_raw_##call *entry;				\
+	struct pt_regs *__regs;						\
+	u64 __count = 1;						\
+	struct task_struct *__task = NULL;				\
+	struct hlist_head *head;					\
+	int __entry_size;						\
+	int __data_size;						\
+	int rctx;							\
+									\
+	__data_size = trace_event_get_offsets_##call(&__data_offsets, args); \
+									\
+	head = this_cpu_ptr(event_call->perf_events);			\
+	if (!bpf_prog_array_valid(event_call) &&			\
+	    __builtin_constant_p(!__task) && !__task &&			\
+	    hlist_empty(head))						\
+		return;							\
+									\
+	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
+			     sizeof(u64));				\
+	__entry_size -= sizeof(u32);					\
+									\
+	entry = perf_trace_buf_alloc(__entry_size, &__regs, &rctx);	\
+	if (!entry)							\
+		return;							\
+									\
+	perf_fetch_caller_regs(__regs);					\
+									\
+	tstruct								\
+									\
+	{ assign; }							\
+									\
+	perf_trace_run_bpf_submit(entry, __entry_size, rctx,		\
+				  event_call, __count, __regs,		\
+				  head, __task);			\
+}
+
+/*
+ * Define unused __count and __task variables to use @args to pass
+ * arguments to do_perf_trace_##call. This is needed because the
+ * macros __perf_count and __perf_task introduce the side-effect to
+ * store copies into those local variables.
+ */
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \
+		      PARAMS(assign), PARAMS(print))			\
+static notrace void							\
+perf_trace_##call(void *__data, proto)					\
+{									\
+	u64 __count __attribute__((unused));				\
+	struct task_struct *__task __attribute__((unused));		\
+									\
+	guard(preempt_notrace)();					\
+	do_perf_trace_##call(__data, args);				\
+}
+
+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS(call, proto, args, tstruct, assign, print) \
+__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \
+		      PARAMS(assign), PARAMS(print))			\
+static notrace void							\
+perf_trace_##call(void *__data, proto)					\
+{									\
+	u64 __count __attribute__((unused));				\
+	struct task_struct *__task __attribute__((unused));		\
+									\
+	might_fault();							\
+	guard(preempt_notrace)();					\
+	do_perf_trace_##call(__data, args);				\
+}
+
+/*
+ * This part is compiled out, it is only here as a build time check
+ * to make sure that if the tracepoint handling changes, the
+ * perf probe will fail to compile unless it too is updated.
+ */
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args)			\
+static inline void perf_test_probe_##call(void)				\
+{									\
+	check_trace_callback_type_##call(perf_trace_##template);	\
+}
+
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef __DECLARE_EVENT_CLASS
+
+#endif /* CONFIG_PERF_EVENTS */