From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug 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 Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- .../access-controllers/access-controllers.yaml | 84 ++++++++++++++++++++++ 1 file changed, 84 insertions(+) create mode 100644 Documentation/devicetree/bindings/access-controllers/access-controllers.yaml (limited to 'Documentation/devicetree/bindings/access-controllers') diff --git a/Documentation/devicetree/bindings/access-controllers/access-controllers.yaml b/Documentation/devicetree/bindings/access-controllers/access-controllers.yaml new file mode 100644 index 000000000..99e2865f0 --- /dev/null +++ b/Documentation/devicetree/bindings/access-controllers/access-controllers.yaml @@ -0,0 +1,84 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/access-controllers/access-controllers.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Generic Domain Access Controllers + +maintainers: + - Oleksii Moisieiev + +description: |+ + Common access controllers properties + + Access controllers are in charge of stating which of the hardware blocks under + their responsibility (their domain) can be accesssed by which compartment. A + compartment can be a cluster of CPUs (or coprocessors), a range of addresses + or a group of hardware blocks. An access controller's domain is the set of + resources covered by the access controller. + + This device tree binding can be used to bind devices to their access + controller provided by access-controllers property. In this case, the device + is a consumer and the access controller is the provider. + + An access controller can be represented by any node in the device tree and + can provide one or more configuration parameters, needed to control parameters + of the consumer device. A consumer node can refer to the provider by phandle + and a set of phandle arguments, specified by '#access-controller-cells' + property in the access controller node. + + Access controllers are typically used to set/read the permissions of a + hardware block and grant access to it. Any of which depends on the access + controller. The capabilities of each access controller are defined by the + binding of the access controller device. + + Each node can be a consumer for the several access controllers. + +# always select the core schema +select: true + +properties: + "#access-controller-cells": + description: + Number of cells in an access-controllers specifier; + Can be any value as specified by device tree binding documentation + of a particular provider. The node is an access controller. + + access-controller-names: + $ref: /schemas/types.yaml#/definitions/string-array + description: + A list of access-controllers names, sorted in the same order as + access-controllers entries. Consumer drivers will use + access-controller-names to match with existing access-controllers entries. + + access-controllers: + $ref: /schemas/types.yaml#/definitions/phandle-array + description: + A list of access controller specifiers, as defined by the + bindings of the access-controllers provider. + +additionalProperties: true + +examples: + - | + clock_controller: access-controllers@50000 { + reg = <0x50000 0x400>; + #access-controller-cells = <2>; + }; + + bus_controller: bus@60000 { + reg = <0x60000 0x10000>; + #address-cells = <1>; + #size-cells = <1>; + ranges; + #access-controller-cells = <3>; + + uart4: serial@60100 { + reg = <0x60100 0x400>; + clocks = <&clk_serial>; + access-controllers = <&clock_controller 1 2>, + <&bus_controller 1 3 5>; + access-controller-names = "clock", "bus"; + }; + }; -- cgit v1.3.1