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, 152 insertions, 0 deletions

diff --git a/Documentation/driver-api/interconnect.rst b/Documentation/driver-api/interconnect.rst
new file mode 100644
index 000000000..cebb77b49
--- /dev/null
+++ b/Documentation/driver-api/interconnect.rst
@@ -0,0 +1,152 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================================
+Generic System Interconnect Subsystem
+=====================================
+
+Introduction
+------------
+
+This framework is designed to provide a standard kernel interface to control
+the settings of the interconnects on an SoC. These settings can be throughput,
+latency and priority between multiple interconnected devices or functional
+blocks. This can be controlled dynamically in order to save power or provide
+maximum performance.
+
+The interconnect bus is hardware with configurable parameters, which can be
+set on a data path according to the requests received from various drivers.
+An example of interconnect buses are the interconnects between various
+components or functional blocks in chipsets. There can be multiple interconnects
+on an SoC that can be multi-tiered.
+
+Below is a simplified diagram of a real-world SoC interconnect bus topology.
+
+::
+
+ +----------------+    +----------------+
+ | HW Accelerator |--->|      M NoC     |<---------------+
+ +----------------+    +----------------+                |
+                         |      |                    +------------+
+  +-----+  +-------------+      V       +------+     |            |
+  | DDR |  |                +--------+  | PCIe |     |            |
+  +-----+  |                | Slaves |  +------+     |            |
+    ^ ^    |                +--------+     |         |   C NoC    |
+    | |    V                               V         |            |
+ +------------------+   +------------------------+   |            |   +-----+
+ |                  |-->|                        |-->|            |-->| CPU |
+ |                  |-->|                        |<--|            |   +-----+
+ |     Mem NoC      |   |         S NoC          |   +------------+
+ |                  |<--|                        |---------+    |
+ |                  |<--|                        |<------+ |    |   +--------+
+ +------------------+   +------------------------+       | |    +-->| Slaves |
+   ^  ^    ^    ^          ^                             | |        +--------+
+   |  |    |    |          |                             | V
+ +------+  |  +-----+   +-----+  +---------+   +----------------+   +--------+
+ | CPUs |  |  | GPU |   | DSP |  | Masters |-->|       P NoC    |-->| Slaves |
+ +------+  |  +-----+   +-----+  +---------+   +----------------+   +--------+
+           |
+       +-------+
+       | Modem |
+       +-------+
+
+Terminology
+-----------
+
+Interconnect provider is the software definition of the interconnect hardware.
+The interconnect providers on the above diagram are M NoC, S NoC, C NoC, P NoC
+and Mem NoC.
+
+Interconnect node is the software definition of the interconnect hardware
+port. Each interconnect provider consists of multiple interconnect nodes,
+which are connected to other SoC components including other interconnect
+providers. The point on the diagram where the CPUs connect to the memory is
+called an interconnect node, which belongs to the Mem NoC interconnect provider.
+
+Interconnect endpoints are the first or the last element of the path. Every
+endpoint is a node, but not every node is an endpoint.
+
+Interconnect path is everything between two endpoints including all the nodes
+that have to be traversed to reach from a source to destination node. It may
+include multiple master-slave pairs across several interconnect providers.
+
+Interconnect consumers are the entities which make use of the data paths exposed
+by the providers. The consumers send requests to providers requesting various
+throughput, latency and priority. Usually the consumers are device drivers, that
+send request based on their needs. An example for a consumer is a video decoder
+that supports various formats and image sizes.
+
+Interconnect providers
+----------------------
+
+Interconnect provider is an entity that implements methods to initialize and
+configure interconnect bus hardware. The interconnect provider drivers should
+be registered with the interconnect provider core.
+
+.. kernel-doc:: include/linux/interconnect-provider.h
+
+.. kernel-doc:: drivers/interconnect/core.c
+   :functions: icc_provider_init icc_provider_register icc_provider_deregister
+               icc_node_create icc_node_create_dyn icc_node_destroy
+               icc_node_add icc_node_del icc_nodes_remove icc_node_set_name
+               icc_link_create icc_link_nodes
+
+Interconnect consumers
+----------------------
+
+Interconnect consumers are the clients which use the interconnect APIs to
+get paths between endpoints and set their bandwidth/latency/QoS requirements
+for these interconnect paths.
+
+.. kernel-doc:: drivers/interconnect/core.c
+   :functions: devm_of_icc_get of_icc_get_by_index of_icc_get icc_get
+               icc_put icc_enable icc_disable icc_set_bw icc_set_tag
+               icc_get_name
+
+.. kernel-doc:: drivers/interconnect/bulk.c
+
+Interconnect debugfs interfaces
+-------------------------------
+
+Like several other subsystems interconnect will create some files for debugging
+and introspection. Files in debugfs are not considered ABI so application
+software shouldn't rely on format details change between kernel versions.
+
+``/sys/kernel/debug/interconnect/interconnect_summary``:
+
+Show all interconnect nodes in the system with their aggregated bandwidth
+request. Indented under each node show bandwidth requests from each device.
+
+``/sys/kernel/debug/interconnect/interconnect_graph``:
+
+Show the interconnect graph in the graphviz dot format. It shows all
+interconnect nodes and links in the system and groups together nodes from the
+same provider as subgraphs. The format is human-readable and can also be piped
+through dot to generate diagrams in many graphical formats::
+
+        $ cat /sys/kernel/debug/interconnect/interconnect_graph | \
+                dot -Tsvg > interconnect_graph.svg
+
+The ``test-client`` directory provides interfaces for issuing BW requests to
+any arbitrary path. Note that for safety reasons, this feature is disabled by
+default without a Kconfig to enable it. Enabling it requires code changes to
+``#define INTERCONNECT_ALLOW_WRITE_DEBUGFS``. Example usage::
+
+        cd /sys/kernel/debug/interconnect/test-client/
+
+        # Configure node endpoints for the path from CPU to DDR on
+        # qcom/sm8550.
+        echo chm_apps > src_node
+        echo ebi > dst_node
+
+        # Get path between src_node and dst_node. This is only
+        # necessary after updating the node endpoints.
+        echo 1 > get
+
+        # Set desired BW to 1GBps avg and 2GBps peak.
+        echo 1000000 > avg_bw
+        echo 2000000 > peak_bw
+
+        # Vote for avg_bw and peak_bw on the latest path from "get".
+        # Voting for multiple paths is possible by repeating this
+        # process for different nodes endpoints.
+        echo 1 > commit