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, 67 insertions, 0 deletions

diff --git a/drivers/char/tpm/tpm-dev.c b/drivers/char/tpm/tpm-dev.c
new file mode 100644
index 000000000..74488f0a7
--- /dev/null
+++ b/drivers/char/tpm/tpm-dev.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004 IBM Corporation
+ * Authors:
+ * Leendert van Doorn <leendert@watson.ibm.com>
+ * Dave Safford <safford@watson.ibm.com>
+ * Reiner Sailer <sailer@watson.ibm.com>
+ * Kylene Hall <kjhall@us.ibm.com>
+ *
+ * Copyright (C) 2013 Obsidian Research Corp
+ * Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
+ *
+ * Device file system interface to the TPM
+ */
+#include <linux/slab.h>
+#include "tpm-dev.h"
+
+static int tpm_open(struct inode *inode, struct file *file)
+{
+	struct tpm_chip *chip;
+	struct file_priv *priv;
+
+	chip = container_of(inode->i_cdev, struct tpm_chip, cdev);
+
+	/* It's assured that the chip will be opened just once,
+	 * by the check of is_open variable, which is protected
+	 * by driver_lock. */
+	if (test_and_set_bit(0, &chip->is_open)) {
+		dev_dbg(&chip->dev, "Another process owns this TPM\n");
+		return -EBUSY;
+	}
+
+	priv = kzalloc_obj(*priv);
+	if (priv == NULL)
+		goto out;
+
+	tpm_common_open(file, chip, priv, NULL);
+
+	return nonseekable_open(inode, file);
+
+ out:
+	clear_bit(0, &chip->is_open);
+	return -ENOMEM;
+}
+
+/*
+ * Called on file close
+ */
+static int tpm_release(struct inode *inode, struct file *file)
+{
+	struct file_priv *priv = file->private_data;
+
+	tpm_common_release(file, priv);
+	clear_bit(0, &priv->chip->is_open);
+	kfree(priv);
+
+	return 0;
+}
+
+const struct file_operations tpm_fops = {
+	.owner = THIS_MODULE,
+	.open = tpm_open,
+	.read = tpm_common_read,
+	.write = tpm_common_write,
+	.poll = tpm_common_poll,
+	.release = tpm_release,
+};