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, 174 insertions, 0 deletions

diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
new file mode 100644
index 000000000..b2ba5a805
--- /dev/null
+++ b/include/trace/define_trace.h
@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Trace files that want to automate creation of all tracepoints defined
+ * in their file should include this file. The following are macros that the
+ * trace file may define:
+ *
+ * TRACE_SYSTEM defines the system the tracepoint is for
+ *
+ * TRACE_INCLUDE_FILE if the file name is something other than TRACE_SYSTEM.h
+ *     This macro may be defined to tell define_trace.h what file to include.
+ *     Note, leave off the ".h".
+ *
+ * TRACE_INCLUDE_PATH if the path is something other than core kernel include/trace
+ *     then this macro can define the path to use. Note, the path is relative to
+ *     define_trace.h, not the file including it. Full path names for out of tree
+ *     modules must be used.
+ */
+
+#ifdef CREATE_TRACE_POINTS
+
+/* Prevent recursion */
+#undef CREATE_TRACE_POINTS
+
+#include <linux/stringify.h>
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
+
+#undef TRACE_EVENT_CONDITION
+#define TRACE_EVENT_CONDITION(name, proto, args, cond, tstruct, assign, print) \
+	TRACE_EVENT(name,						\
+		PARAMS(proto),						\
+		PARAMS(args),						\
+		PARAMS(tstruct),					\
+		PARAMS(assign),						\
+		PARAMS(print))
+
+#undef TRACE_EVENT_FN
+#define TRACE_EVENT_FN(name, proto, args, tstruct,		\
+		assign, print, reg, unreg)			\
+	DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args))
+
+#undef TRACE_EVENT_FN_COND
+#define TRACE_EVENT_FN_COND(name, proto, args, cond, tstruct,		\
+		assign, print, reg, unreg)			\
+	DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args))
+
+#undef TRACE_EVENT_SYSCALL
+#define TRACE_EVENT_SYSCALL(name, proto, args, struct, assign, print, reg, unreg) \
+	DEFINE_TRACE_SYSCALL(name, reg, unreg, PARAMS(proto), PARAMS(args))
+
+#undef TRACE_EVENT_NOP
+#define TRACE_EVENT_NOP(name, proto, args, struct, assign, print)
+
+#undef DEFINE_EVENT_NOP
+#define DEFINE_EVENT_NOP(template, name, proto, args)
+
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args) \
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
+
+#undef DEFINE_EVENT_FN
+#define DEFINE_EVENT_FN(template, name, proto, args, reg, unreg) \
+	DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args))
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
+
+#undef DEFINE_EVENT_CONDITION
+#define DEFINE_EVENT_CONDITION(template, name, proto, args, cond) \
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
+#undef DECLARE_TRACE
+#define DECLARE_TRACE(name, proto, args)	\
+	DEFINE_TRACE(name##_tp, PARAMS(proto), PARAMS(args))
+
+#undef DECLARE_TRACE_CONDITION
+#define DECLARE_TRACE_CONDITION(name, proto, args, cond)	\
+	DEFINE_TRACE(name##_tp, PARAMS(proto), PARAMS(args))
+
+#undef DECLARE_TRACE_EVENT
+#define DECLARE_TRACE_EVENT(name, proto, args)	\
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
+
+#undef DECLARE_TRACE_EVENT_CONDITION
+#define DECLARE_TRACE_EVENT_CONDITION(name, proto, args, cond)	\
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
+
+/* If requested, create helpers for calling these tracepoints from Rust. */
+#ifdef CREATE_RUST_TRACE_POINTS
+#undef DEFINE_RUST_DO_TRACE
+#define DEFINE_RUST_DO_TRACE(name, proto, args)	\
+	__DEFINE_RUST_DO_TRACE(name, PARAMS(proto), PARAMS(args))
+#endif
+
+#undef TRACE_INCLUDE
+#undef __TRACE_INCLUDE
+
+#ifndef TRACE_INCLUDE_FILE
+# define TRACE_INCLUDE_FILE TRACE_SYSTEM
+# define UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifndef TRACE_INCLUDE_PATH
+# define __TRACE_INCLUDE(system) <trace/events/system.h>
+# define UNDEF_TRACE_INCLUDE_PATH
+#else
+# define __TRACE_INCLUDE(system) __stringify(TRACE_INCLUDE_PATH/system.h)
+#endif
+
+# define TRACE_INCLUDE(system) __TRACE_INCLUDE(system)
+
+/* Let the trace headers be reread */
+#define TRACE_HEADER_MULTI_READ
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/* Make all open coded DECLARE_TRACE nops */
+#undef DECLARE_TRACE
+#define DECLARE_TRACE(name, proto, args)
+#undef DECLARE_TRACE_CONDITION
+#define DECLARE_TRACE_CONDITION(name, proto, args, cond)
+
+#undef DECLARE_TRACE_EVENT
+#define DECLARE_TRACE_EVENT(name, proto, args)
+#undef DECLARE_TRACE_EVENT_CONDITION
+#define DECLARE_TRACE_EVENT_CONDITION(name, proto, args, cond)
+
+#ifdef TRACEPOINTS_ENABLED
+#include <trace/trace_events.h>
+#include <trace/perf.h>
+#include <trace/bpf_probe.h>
+#endif
+
+#undef TRACE_EVENT
+#undef TRACE_EVENT_FN
+#undef TRACE_EVENT_FN_COND
+#undef TRACE_EVENT_SYSCALL
+#undef TRACE_EVENT_CONDITION
+#undef TRACE_EVENT_NOP
+#undef DEFINE_EVENT_NOP
+#undef DECLARE_EVENT_CLASS
+#undef DEFINE_EVENT
+#undef DEFINE_EVENT_FN
+#undef DEFINE_EVENT_PRINT
+#undef DEFINE_EVENT_CONDITION
+#undef TRACE_HEADER_MULTI_READ
+#undef DECLARE_TRACE
+#undef DECLARE_TRACE_CONDITION
+#undef DECLARE_TRACE_EVENT
+#undef DECLARE_TRACE_EVENT_CONDITION
+
+/* Only undef what we defined in this file */
+#ifdef UNDEF_TRACE_INCLUDE_FILE
+# undef TRACE_INCLUDE_FILE
+# undef UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifdef UNDEF_TRACE_INCLUDE_PATH
+# undef TRACE_INCLUDE_PATH
+# undef UNDEF_TRACE_INCLUDE_PATH
+#endif
+
+#ifdef CREATE_RUST_TRACE_POINTS
+# undef DEFINE_RUST_DO_TRACE
+# define DEFINE_RUST_DO_TRACE(name, proto, args)
+#endif
+
+/* We may be processing more files */
+#define CREATE_TRACE_POINTS
+
+#endif /* CREATE_TRACE_POINTS */