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, 76 insertions, 0 deletions

diff --git a/fs/9p/cache.c b/fs/9p/cache.c
new file mode 100644
index 000000000..12c0ae29f
--- /dev/null
+++ b/fs/9p/cache.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * V9FS cache definitions.
+ *
+ *  Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu>
+ */
+
+#include <linux/jiffies.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <net/9p/9p.h>
+
+#include "v9fs.h"
+#include "cache.h"
+
+int v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses,
+				  const char *dev_name)
+{
+	struct fscache_volume *vcookie;
+	char *name, *p;
+
+	name = kasprintf(GFP_KERNEL, "9p,%s,%s",
+			 dev_name, v9ses->cachetag ?: v9ses->aname);
+	if (!name)
+		return -ENOMEM;
+
+	for (p = name; *p; p++)
+		if (*p == '/')
+			*p = ';';
+
+	vcookie = fscache_acquire_volume(name, NULL, NULL, 0);
+	p9_debug(P9_DEBUG_FSC, "session %p get volume %p (%s)\n",
+		 v9ses, vcookie, name);
+	if (IS_ERR(vcookie)) {
+		if (vcookie != ERR_PTR(-EBUSY)) {
+			kfree(name);
+			return PTR_ERR(vcookie);
+		}
+		pr_err("Cache volume key already in use (%s)\n", name);
+		vcookie = NULL;
+	}
+	v9ses->fscache = vcookie;
+	kfree(name);
+	return 0;
+}
+
+void v9fs_cache_inode_get_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct v9fs_session_info *v9ses;
+	__le32 version;
+	__le64 path;
+
+	if (!S_ISREG(inode->i_mode))
+		return;
+	if (WARN_ON(v9fs_inode_cookie(v9inode)))
+		return;
+
+	version = cpu_to_le32(v9inode->qid.version);
+	path = cpu_to_le64(v9inode->qid.path);
+	v9ses = v9fs_inode2v9ses(inode);
+	v9inode->netfs.cache =
+		fscache_acquire_cookie(v9fs_session_cache(v9ses),
+				       0,
+				       &path, sizeof(path),
+				       &version, sizeof(version),
+				       i_size_read(&v9inode->netfs.inode));
+	if (v9inode->netfs.cache)
+		mapping_set_release_always(inode->i_mapping);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n",
+		 inode, v9fs_inode_cookie(v9inode));
+}