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, 94 insertions, 0 deletions

diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
new file mode 100644
index 000000000..14aa08662
--- /dev/null
+++ b/drivers/dma/Makefile
@@ -0,0 +1,94 @@
+# SPDX-License-Identifier: GPL-2.0
+#dmaengine debug flags
+subdir-ccflags-$(CONFIG_DMADEVICES_DEBUG)  := -DDEBUG
+subdir-ccflags-$(CONFIG_DMADEVICES_VDEBUG) += -DVERBOSE_DEBUG
+
+#core
+obj-$(CONFIG_DMA_ENGINE) += dmaengine.o
+obj-$(CONFIG_DMA_VIRTUAL_CHANNELS) += virt-dma.o
+obj-$(CONFIG_DMA_ACPI) += acpi-dma.o
+obj-$(CONFIG_DMA_OF) += of-dma.o
+
+#dmatest
+obj-$(CONFIG_DMATEST) += dmatest.o
+
+#devices
+obj-$(CONFIG_ALTERA_MSGDMA) += altera-msgdma.o
+obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o
+obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
+obj-$(CONFIG_APPLE_ADMAC) += apple-admac.o
+obj-$(CONFIG_ARM_DMA350) += arm-dma350.o
+obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
+obj-$(CONFIG_AT_XDMAC) += at_xdmac.o
+obj-$(CONFIG_AXI_DMAC) += dma-axi-dmac.o
+obj-$(CONFIG_BCM_SBA_RAID) += bcm-sba-raid.o
+obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o
+obj-$(CONFIG_DMA_JZ4780) += dma-jz4780.o
+obj-$(CONFIG_DMA_SA11X0) += sa11x0-dma.o
+obj-$(CONFIG_DMA_SUN4I) += sun4i-dma.o
+obj-$(CONFIG_DMA_SUN6I) += sun6i-dma.o
+obj-$(CONFIG_DW_AXI_DMAC) += dw-axi-dmac/
+obj-$(CONFIG_DW_DMAC_CORE) += dw/
+obj-$(CONFIG_DW_EDMA) += dw-edma/
+obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
+fsl-edma-trace-$(CONFIG_TRACING) := fsl-edma-trace.o
+CFLAGS_fsl-edma-trace.o := -I$(src)
+obj-$(CONFIG_FSL_DMA) += fsldma.o
+fsl-edma-objs := fsl-edma-main.o fsl-edma-common.o ${fsl-edma-trace-y}
+obj-$(CONFIG_FSL_EDMA) += fsl-edma.o
+mcf-edma-objs := mcf-edma-main.o fsl-edma-common.o ${fsl-edma-trace-y}
+obj-$(CONFIG_MCF_EDMA) += mcf-edma.o
+obj-$(CONFIG_FSL_QDMA) += fsl-qdma.o
+obj-$(CONFIG_FSL_RAID) += fsl_raid.o
+obj-$(CONFIG_HISI_DMA) += hisi_dma.o
+obj-$(CONFIG_HSU_DMA) += hsu/
+obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o
+obj-$(CONFIG_IMX_DMA) += imx-dma.o
+obj-$(CONFIG_IMX_SDMA) += imx-sdma.o
+obj-$(CONFIG_INTEL_IDMA64) += idma64.o
+obj-$(CONFIG_INTEL_IOATDMA) += ioat/
+obj-y += idxd/
+obj-$(CONFIG_K3_DMA) += k3dma.o
+obj-$(CONFIG_LPC18XX_DMAMUX) += lpc18xx-dmamux.o
+obj-$(CONFIG_LPC32XX_DMAMUX) += lpc32xx-dmamux.o
+obj-$(CONFIG_MILBEAUT_HDMAC) += milbeaut-hdmac.o
+obj-$(CONFIG_MILBEAUT_XDMAC) += milbeaut-xdmac.o
+obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
+obj-$(CONFIG_MMP_TDMA) += mmp_tdma.o
+obj-$(CONFIG_MOXART_DMA) += moxart-dma.o
+obj-$(CONFIG_MPC512X_DMA) += mpc512x_dma.o
+obj-$(CONFIG_MV_XOR) += mv_xor.o
+obj-$(CONFIG_MV_XOR_V2) += mv_xor_v2.o
+obj-$(CONFIG_MXS_DMA) += mxs-dma.o
+obj-$(CONFIG_NBPFAXI_DMA) += nbpfaxi.o
+obj-$(CONFIG_OWL_DMA) += owl-dma.o
+obj-$(CONFIG_PCH_DMA) += pch_dma.o
+obj-$(CONFIG_PL330_DMA) += pl330.o
+obj-$(CONFIG_PLX_DMA) += plx_dma.o
+obj-$(CONFIG_PPC_BESTCOMM) += bestcomm/
+obj-$(CONFIG_PXA_DMA) += pxa_dma.o
+obj-$(CONFIG_RENESAS_DMA) += sh/
+obj-$(CONFIG_SF_PDMA) += sf-pdma/
+obj-$(CONFIG_SOPHGO_CV1800B_DMAMUX) += cv1800b-dmamux.o
+obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
+obj-$(CONFIG_SPRD_DMA) += sprd-dma.o
+obj-$(CONFIG_SWITCHTEC_DMA) += switchtec_dma.o
+obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
+obj-$(CONFIG_TEGRA186_GPC_DMA) += tegra186-gpc-dma.o
+obj-$(CONFIG_TEGRA20_APB_DMA) += tegra20-apb-dma.o
+obj-$(CONFIG_TEGRA210_ADMA) += tegra210-adma.o
+obj-$(CONFIG_TIMB_DMA) += timb_dma.o
+obj-$(CONFIG_UNIPHIER_MDMAC) += uniphier-mdmac.o
+obj-$(CONFIG_UNIPHIER_XDMAC) += uniphier-xdmac.o
+obj-$(CONFIG_XGENE_DMA) += xgene-dma.o
+obj-$(CONFIG_ST_FDMA) += st_fdma.o
+obj-$(CONFIG_FSL_DPAA2_QDMA) += fsl-dpaa2-qdma/
+obj-$(CONFIG_INTEL_LDMA) += lgm/
+
+obj-y += amd/
+obj-y += loongson/
+obj-y += mediatek/
+obj-y += qcom/
+obj-y += stm32/
+obj-y += ti/
+obj-y += xilinx/