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, 107 insertions, 0 deletions

diff --git a/drivers/nvmem/meson-efuse.c b/drivers/nvmem/meson-efuse.c
new file mode 100644
index 000000000..d7f9ac99a
--- /dev/null
+++ b/drivers/nvmem/meson-efuse.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Amlogic Meson GX eFuse Driver
+ *
+ * Copyright (c) 2016 Endless Computers, Inc.
+ * Author: Carlo Caione <carlo@endlessm.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/nvmem-provider.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include <linux/firmware/meson/meson_sm.h>
+
+static int meson_efuse_read(void *context, unsigned int offset,
+			    void *val, size_t bytes)
+{
+	struct meson_sm_firmware *fw = context;
+	int ret;
+
+	ret = meson_sm_call_read(fw, (u8 *)val, bytes, SM_EFUSE_READ, offset,
+				 bytes, 0, 0, 0);
+
+	return ret < 0 ? ret : 0;
+}
+
+static int meson_efuse_write(void *context, unsigned int offset,
+			     void *val, size_t bytes)
+{
+	struct meson_sm_firmware *fw = context;
+	int ret;
+
+	ret = meson_sm_call_write(fw, (u8 *)val, bytes, SM_EFUSE_WRITE, offset,
+				  bytes, 0, 0, 0);
+
+	return ret < 0 ? ret : 0;
+}
+
+static const struct of_device_id meson_efuse_match[] = {
+	{ .compatible = "amlogic,meson-gxbb-efuse", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, meson_efuse_match);
+
+static int meson_efuse_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct meson_sm_firmware *fw;
+	struct nvmem_device *nvmem;
+	struct nvmem_config *econfig;
+	struct clk *clk;
+	unsigned int size;
+	struct device_node *sm_np __free(device_node) =
+			of_parse_phandle(pdev->dev.of_node, "secure-monitor", 0);
+
+	if (!sm_np) {
+		dev_err(&pdev->dev, "no secure-monitor node\n");
+		return -ENODEV;
+	}
+
+	fw = meson_sm_get(sm_np);
+	if (!fw)
+		return -EPROBE_DEFER;
+
+	clk = devm_clk_get_enabled(dev, NULL);
+	if (IS_ERR(clk))
+		return dev_err_probe(dev, PTR_ERR(clk), "failed to get efuse gate");
+
+	if (meson_sm_call(fw, SM_EFUSE_USER_MAX, &size, 0, 0, 0, 0, 0) < 0) {
+		dev_err(dev, "failed to get max user");
+		return -EINVAL;
+	}
+
+	econfig = devm_kzalloc(dev, sizeof(*econfig), GFP_KERNEL);
+	if (!econfig)
+		return -ENOMEM;
+
+	econfig->dev = dev;
+	econfig->name = dev_name(dev);
+	econfig->add_legacy_fixed_of_cells = true;
+	econfig->stride = 1;
+	econfig->word_size = 1;
+	econfig->reg_read = meson_efuse_read;
+	econfig->reg_write = meson_efuse_write;
+	econfig->size = size;
+	econfig->priv = fw;
+
+	nvmem = devm_nvmem_register(&pdev->dev, econfig);
+
+	return PTR_ERR_OR_ZERO(nvmem);
+}
+
+static struct platform_driver meson_efuse_driver = {
+	.probe = meson_efuse_probe,
+	.driver = {
+		.name = "meson-efuse",
+		.of_match_table = meson_efuse_match,
+	},
+};
+
+module_platform_driver(meson_efuse_driver);
+
+MODULE_AUTHOR("Carlo Caione <carlo@endlessm.com>");
+MODULE_DESCRIPTION("Amlogic Meson GX NVMEM driver");
+MODULE_LICENSE("GPL v2");