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, 119 insertions, 0 deletions

diff --git a/include/dt-bindings/clock/imx7ulp-clock.h b/include/dt-bindings/clock/imx7ulp-clock.h
new file mode 100644
index 000000000..b58370d14
--- /dev/null
+++ b/include/dt-bindings/clock/imx7ulp-clock.h
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2016 Freescale Semiconductor, Inc.
+ * Copyright 2017~2018 NXP
+ *
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_IMX7ULP_H
+#define __DT_BINDINGS_CLOCK_IMX7ULP_H
+
+/* SCG1 */
+
+#define IMX7ULP_CLK_DUMMY		0
+#define IMX7ULP_CLK_ROSC		1
+#define IMX7ULP_CLK_SOSC		2
+#define IMX7ULP_CLK_FIRC		3
+#define IMX7ULP_CLK_SPLL_PRE_SEL	4
+#define IMX7ULP_CLK_SPLL_PRE_DIV	5
+#define IMX7ULP_CLK_SPLL		6
+#define IMX7ULP_CLK_SPLL_POST_DIV1	7
+#define IMX7ULP_CLK_SPLL_POST_DIV2	8
+#define IMX7ULP_CLK_SPLL_PFD0		9
+#define IMX7ULP_CLK_SPLL_PFD1		10
+#define IMX7ULP_CLK_SPLL_PFD2		11
+#define IMX7ULP_CLK_SPLL_PFD3		12
+#define IMX7ULP_CLK_SPLL_PFD_SEL	13
+#define IMX7ULP_CLK_SPLL_SEL		14
+#define IMX7ULP_CLK_APLL_PRE_SEL	15
+#define IMX7ULP_CLK_APLL_PRE_DIV	16
+#define IMX7ULP_CLK_APLL		17
+#define IMX7ULP_CLK_APLL_POST_DIV1	18
+#define IMX7ULP_CLK_APLL_POST_DIV2	19
+#define IMX7ULP_CLK_APLL_PFD0		20
+#define IMX7ULP_CLK_APLL_PFD1		21
+#define IMX7ULP_CLK_APLL_PFD2		22
+#define IMX7ULP_CLK_APLL_PFD3		23
+#define IMX7ULP_CLK_APLL_PFD_SEL	24
+#define IMX7ULP_CLK_APLL_SEL		25
+#define IMX7ULP_CLK_UPLL		26
+#define IMX7ULP_CLK_SYS_SEL		27
+#define IMX7ULP_CLK_CORE_DIV		28
+#define IMX7ULP_CLK_BUS_DIV		29
+#define IMX7ULP_CLK_PLAT_DIV		30
+#define IMX7ULP_CLK_DDR_SEL		31
+#define IMX7ULP_CLK_DDR_DIV		32
+#define IMX7ULP_CLK_NIC_SEL		33
+#define IMX7ULP_CLK_NIC0_DIV		34
+#define IMX7ULP_CLK_GPU_DIV		35
+#define IMX7ULP_CLK_NIC1_DIV		36
+#define IMX7ULP_CLK_NIC1_BUS_DIV	37
+#define IMX7ULP_CLK_NIC1_EXT_DIV	38
+/* IMX7ULP_CLK_MIPI_PLL is unsupported and shouldn't be used in DT */
+#define IMX7ULP_CLK_MIPI_PLL		39
+#define IMX7ULP_CLK_SIRC		40
+#define IMX7ULP_CLK_SOSC_BUS_CLK	41
+#define IMX7ULP_CLK_FIRC_BUS_CLK	42
+#define IMX7ULP_CLK_SPLL_BUS_CLK	43
+#define IMX7ULP_CLK_HSRUN_SYS_SEL	44
+#define IMX7ULP_CLK_HSRUN_CORE_DIV	45
+
+#define IMX7ULP_CLK_CORE		46
+#define IMX7ULP_CLK_HSRUN_CORE		47
+
+#define IMX7ULP_CLK_SCG1_END		48
+
+/* PCC2 */
+#define IMX7ULP_CLK_DMA1		0
+#define IMX7ULP_CLK_RGPIO2P1		1
+#define IMX7ULP_CLK_FLEXBUS		2
+#define IMX7ULP_CLK_SEMA42_1		3
+#define IMX7ULP_CLK_DMA_MUX1		4
+#define IMX7ULP_CLK_CAAM		6
+#define IMX7ULP_CLK_LPTPM4		7
+#define IMX7ULP_CLK_LPTPM5		8
+#define IMX7ULP_CLK_LPIT1		9
+#define IMX7ULP_CLK_LPSPI2		10
+#define IMX7ULP_CLK_LPSPI3		11
+#define IMX7ULP_CLK_LPI2C4		12
+#define IMX7ULP_CLK_LPI2C5		13
+#define IMX7ULP_CLK_LPUART4		14
+#define IMX7ULP_CLK_LPUART5		15
+#define IMX7ULP_CLK_FLEXIO1		16
+#define IMX7ULP_CLK_USB0		17
+#define IMX7ULP_CLK_USB1		18
+#define IMX7ULP_CLK_USB_PHY		19
+#define IMX7ULP_CLK_USB_PL301		20
+#define IMX7ULP_CLK_USDHC0		21
+#define IMX7ULP_CLK_USDHC1		22
+#define IMX7ULP_CLK_WDG1		23
+#define IMX7ULP_CLK_WDG2		24
+
+#define IMX7ULP_CLK_PCC2_END		25
+
+/* PCC3 */
+#define IMX7ULP_CLK_LPTPM6		0
+#define IMX7ULP_CLK_LPTPM7		1
+#define IMX7ULP_CLK_LPI2C6		2
+#define IMX7ULP_CLK_LPI2C7		3
+#define IMX7ULP_CLK_LPUART6		4
+#define IMX7ULP_CLK_LPUART7		5
+#define IMX7ULP_CLK_VIU			6
+#define IMX7ULP_CLK_DSI			7
+#define IMX7ULP_CLK_LCDIF		8
+#define IMX7ULP_CLK_MMDC		9
+#define IMX7ULP_CLK_PCTLC		10
+#define IMX7ULP_CLK_PCTLD		11
+#define IMX7ULP_CLK_PCTLE		12
+#define IMX7ULP_CLK_PCTLF		13
+#define IMX7ULP_CLK_GPU3D		14
+#define IMX7ULP_CLK_GPU2D		15
+
+#define IMX7ULP_CLK_PCC3_END		16
+
+/* SMC1 */
+#define IMX7ULP_CLK_ARM			0
+
+#define IMX7ULP_CLK_SMC1_END		1
+
+#endif /* __DT_BINDINGS_CLOCK_IMX7ULP_H */