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, 65 insertions, 0 deletions

diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
new file mode 100644
index 000000000..61ac62c3f
--- /dev/null
+++ b/fs/proc/thread_self.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cache.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/pid_namespace.h>
+#include "internal.h"
+
+/*
+ * /proc/thread_self:
+ */
+static const char *proc_thread_self_get_link(struct dentry *dentry,
+					     struct inode *inode,
+					     struct delayed_call *done)
+{
+	struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
+	pid_t tgid = task_tgid_nr_ns(current, ns);
+	pid_t pid = task_pid_nr_ns(current, ns);
+	char *name;
+
+	if (!pid)
+		return ERR_PTR(-ENOENT);
+	name = kmalloc(10 + 6 + 10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC);
+	if (unlikely(!name))
+		return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD);
+	sprintf(name, "%u/task/%u", tgid, pid);
+	set_delayed_call(done, kfree_link, name);
+	return name;
+}
+
+static const struct inode_operations proc_thread_self_inode_operations = {
+	.get_link	= proc_thread_self_get_link,
+};
+
+unsigned thread_self_inum __ro_after_init;
+
+int proc_setup_thread_self(struct super_block *s)
+{
+	struct dentry *thread_self;
+	int ret = -ENOMEM;
+
+	thread_self = d_alloc_name(s->s_root, "thread-self");
+	if (thread_self) {
+		struct inode *inode = new_inode(s);
+		if (inode) {
+			inode->i_ino = thread_self_inum;
+			simple_inode_init_ts(inode);
+			inode->i_mode = S_IFLNK | S_IRWXUGO;
+			inode->i_uid = GLOBAL_ROOT_UID;
+			inode->i_gid = GLOBAL_ROOT_GID;
+			inode->i_op = &proc_thread_self_inode_operations;
+			d_make_persistent(thread_self, inode);
+			ret = 0;
+		}
+		dput(thread_self);
+	}
+
+	if (ret)
+		pr_err("proc_fill_super: can't allocate /proc/thread-self\n");
+	return ret;
+}
+
+void __init proc_thread_self_init(void)
+{
+	proc_alloc_inum(&thread_self_inum);
+}