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, 149 insertions, 0 deletions

diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c
new file mode 100644
index 000000000..137abbc65
--- /dev/null
+++ b/arch/mips/ath79/common.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Atheros AR71XX/AR724X/AR913X common routines
+ *
+ *  Copyright (C) 2010-2011 Jaiganesh Narayanan <jnarayanan@atheros.com>
+ *  Copyright (C) 2008-2011 Gabor Juhos <juhosg@openwrt.org>
+ *  Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
+ *
+ *  Parts of this file are based on Atheros' 2.6.15/2.6.31 BSP
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+
+#include <asm/mach-ath79/ath79.h>
+#include <asm/mach-ath79/ar71xx_regs.h>
+#include "common.h"
+
+static DEFINE_SPINLOCK(ath79_device_reset_lock);
+
+u32 ath79_cpu_freq;
+EXPORT_SYMBOL_GPL(ath79_cpu_freq);
+
+u32 ath79_ahb_freq;
+EXPORT_SYMBOL_GPL(ath79_ahb_freq);
+
+u32 ath79_ddr_freq;
+EXPORT_SYMBOL_GPL(ath79_ddr_freq);
+
+enum ath79_soc_type ath79_soc;
+unsigned int ath79_soc_rev;
+
+void __iomem *ath79_pll_base;
+void __iomem *ath79_reset_base;
+EXPORT_SYMBOL_GPL(ath79_reset_base);
+static void __iomem *ath79_ddr_base;
+static void __iomem *ath79_ddr_wb_flush_base;
+static void __iomem *ath79_ddr_pci_win_base;
+
+void ath79_ddr_ctrl_init(void)
+{
+	ath79_ddr_base = ioremap(AR71XX_DDR_CTRL_BASE,
+					 AR71XX_DDR_CTRL_SIZE);
+	if (soc_is_ar913x() || soc_is_ar724x() || soc_is_ar933x()) {
+		ath79_ddr_wb_flush_base = ath79_ddr_base + 0x7c;
+		ath79_ddr_pci_win_base = 0;
+	} else {
+		ath79_ddr_wb_flush_base = ath79_ddr_base + 0x9c;
+		ath79_ddr_pci_win_base = ath79_ddr_base + 0x7c;
+	}
+}
+EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init);
+
+void ath79_ddr_wb_flush(u32 reg)
+{
+	void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4);
+
+	/* Flush the DDR write buffer. */
+	__raw_writel(0x1, flush_reg);
+	while (__raw_readl(flush_reg) & 0x1)
+		;
+
+	/* It must be run twice. */
+	__raw_writel(0x1, flush_reg);
+	while (__raw_readl(flush_reg) & 0x1)
+		;
+}
+EXPORT_SYMBOL_GPL(ath79_ddr_wb_flush);
+
+void ath79_ddr_set_pci_windows(void)
+{
+	BUG_ON(!ath79_ddr_pci_win_base);
+
+	__raw_writel(AR71XX_PCI_WIN0_OFFS, ath79_ddr_pci_win_base + 0x0);
+	__raw_writel(AR71XX_PCI_WIN1_OFFS, ath79_ddr_pci_win_base + 0x4);
+	__raw_writel(AR71XX_PCI_WIN2_OFFS, ath79_ddr_pci_win_base + 0x8);
+	__raw_writel(AR71XX_PCI_WIN3_OFFS, ath79_ddr_pci_win_base + 0xc);
+	__raw_writel(AR71XX_PCI_WIN4_OFFS, ath79_ddr_pci_win_base + 0x10);
+	__raw_writel(AR71XX_PCI_WIN5_OFFS, ath79_ddr_pci_win_base + 0x14);
+	__raw_writel(AR71XX_PCI_WIN6_OFFS, ath79_ddr_pci_win_base + 0x18);
+	__raw_writel(AR71XX_PCI_WIN7_OFFS, ath79_ddr_pci_win_base + 0x1c);
+}
+EXPORT_SYMBOL_GPL(ath79_ddr_set_pci_windows);
+
+void ath79_device_reset_set(u32 mask)
+{
+	unsigned long flags;
+	u32 reg;
+	u32 t;
+
+	if (soc_is_ar71xx())
+		reg = AR71XX_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar724x())
+		reg = AR724X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar913x())
+		reg = AR913X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar933x())
+		reg = AR933X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar934x())
+		reg = AR934X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca953x())
+		reg = QCA953X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca955x())
+		reg = QCA955X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		reg = QCA956X_RESET_REG_RESET_MODULE;
+	else
+		BUG();
+
+	spin_lock_irqsave(&ath79_device_reset_lock, flags);
+	t = ath79_reset_rr(reg);
+	ath79_reset_wr(reg, t | mask);
+	spin_unlock_irqrestore(&ath79_device_reset_lock, flags);
+}
+EXPORT_SYMBOL_GPL(ath79_device_reset_set);
+
+void ath79_device_reset_clear(u32 mask)
+{
+	unsigned long flags;
+	u32 reg;
+	u32 t;
+
+	if (soc_is_ar71xx())
+		reg = AR71XX_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar724x())
+		reg = AR724X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar913x())
+		reg = AR913X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar933x())
+		reg = AR933X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar934x())
+		reg = AR934X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca953x())
+		reg = QCA953X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca955x())
+		reg = QCA955X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		reg = QCA956X_RESET_REG_RESET_MODULE;
+	else
+		BUG();
+
+	spin_lock_irqsave(&ath79_device_reset_lock, flags);
+	t = ath79_reset_rr(reg);
+	ath79_reset_wr(reg, t & ~mask);
+	spin_unlock_irqrestore(&ath79_device_reset_lock, flags);
+}
+EXPORT_SYMBOL_GPL(ath79_device_reset_clear);