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, 39 insertions, 0 deletions

diff --git a/Documentation/devicetree/bindings/openrisc/opencores/or1ksim.txt b/Documentation/devicetree/bindings/openrisc/opencores/or1ksim.txt
new file mode 100644
index 000000000..4950c794e
--- /dev/null
+++ b/Documentation/devicetree/bindings/openrisc/opencores/or1ksim.txt
@@ -0,0 +1,39 @@
+OpenRISC Generic SoC
+====================
+
+Boards and FPGA SoC's which support the OpenRISC standard platform.  The
+platform essentially follows the conventions of the OpenRISC architecture
+specification, however some aspects, such as the boot protocol have been defined
+by the Linux port.
+
+Required properties
+-------------------
+ - compatible: Must include "opencores,or1ksim"
+
+CPU nodes:
+----------
+A "cpus" node is required.  Required properties:
+ - #address-cells: Must be 1.
+ - #size-cells: Must be 0.
+A CPU sub-node is also required for at least CPU 0.  Since the topology may
+be probed via CPS, it is not necessary to specify secondary CPUs.  Required
+properties:
+ - compatible: Must be "opencores,or1200-rtlsvn481".
+ - reg: CPU number.
+ - clock-frequency: The CPU clock frequency in Hz.
+Example:
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu@0 {
+			compatible = "opencores,or1200-rtlsvn481";
+			reg = <0>;
+			clock-frequency = <20000000>;
+		};
+	};
+
+
+Boot protocol
+-------------
+The bootloader may pass the following arguments to the kernel:
+ - r3:  address of a flattened device-tree blob or 0x0.