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, 141 insertions, 0 deletions

diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c
new file mode 100644
index 000000000..a676084be
--- /dev/null
+++ b/fs/squashfs/decompressor.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * decompressor.c
+ */
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "decompressor.h"
+#include "squashfs.h"
+#include "page_actor.h"
+
+/*
+ * This file (and decompressor.h) implements a decompressor framework for
+ * Squashfs, allowing multiple decompressors to be easily supported
+ */
+
+static const struct squashfs_decompressor squashfs_lzma_unsupported_comp_ops = {
+	NULL, NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0
+};
+
+#ifndef CONFIG_SQUASHFS_LZ4
+static const struct squashfs_decompressor squashfs_lz4_comp_ops = {
+	NULL, NULL, NULL, NULL, LZ4_COMPRESSION, "lz4", 0
+};
+#endif
+
+#ifndef CONFIG_SQUASHFS_LZO
+static const struct squashfs_decompressor squashfs_lzo_comp_ops = {
+	NULL, NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0
+};
+#endif
+
+#ifndef CONFIG_SQUASHFS_XZ
+static const struct squashfs_decompressor squashfs_xz_comp_ops = {
+	NULL, NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0
+};
+#endif
+
+#ifndef CONFIG_SQUASHFS_ZLIB
+static const struct squashfs_decompressor squashfs_zlib_comp_ops = {
+	NULL, NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0
+};
+#endif
+
+#ifndef CONFIG_SQUASHFS_ZSTD
+static const struct squashfs_decompressor squashfs_zstd_comp_ops = {
+	NULL, NULL, NULL, NULL, ZSTD_COMPRESSION, "zstd", 0
+};
+#endif
+
+static const struct squashfs_decompressor squashfs_unknown_comp_ops = {
+	NULL, NULL, NULL, NULL, 0, "unknown", 0
+};
+
+static const struct squashfs_decompressor *decompressor[] = {
+	&squashfs_zlib_comp_ops,
+	&squashfs_lz4_comp_ops,
+	&squashfs_lzo_comp_ops,
+	&squashfs_xz_comp_ops,
+	&squashfs_lzma_unsupported_comp_ops,
+	&squashfs_zstd_comp_ops,
+	&squashfs_unknown_comp_ops
+};
+
+
+const struct squashfs_decompressor *squashfs_lookup_decompressor(int id)
+{
+	int i;
+
+	for (i = 0; decompressor[i]->id; i++)
+		if (id == decompressor[i]->id)
+			break;
+
+	return decompressor[i];
+}
+
+
+static void *get_comp_opts(struct super_block *sb, unsigned short flags)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	void *buffer = NULL, *comp_opts;
+	struct squashfs_page_actor *actor = NULL;
+	int length = 0;
+
+	/*
+	 * Read decompressor specific options from file system if present
+	 */
+	if (SQUASHFS_COMP_OPTS(flags)) {
+		buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		if (buffer == NULL) {
+			comp_opts = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+
+		actor = squashfs_page_actor_init(&buffer, 1, 0);
+		if (actor == NULL) {
+			comp_opts = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+
+		length = squashfs_read_data(sb,
+			sizeof(struct squashfs_super_block), 0, NULL, actor);
+
+		if (length < 0) {
+			comp_opts = ERR_PTR(length);
+			goto out;
+		}
+	}
+
+	comp_opts = squashfs_comp_opts(msblk, buffer, length);
+
+out:
+	kfree(actor);
+	kfree(buffer);
+	return comp_opts;
+}
+
+
+void *squashfs_decompressor_setup(struct super_block *sb, unsigned short flags)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	void *stream, *comp_opts = get_comp_opts(sb, flags);
+
+	if (IS_ERR(comp_opts))
+		return comp_opts;
+
+	stream = msblk->thread_ops->create(msblk, comp_opts);
+	if (IS_ERR(stream))
+		kfree(comp_opts);
+
+	return stream;
+}