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, 36 insertions, 0 deletions

diff --git a/Documentation/filesystems/devpts.rst b/Documentation/filesystems/devpts.rst
new file mode 100644
index 000000000..b6324ab19
--- /dev/null
+++ b/Documentation/filesystems/devpts.rst
@@ -0,0 +1,36 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+The Devpts Filesystem
+=====================
+
+Each mount of the devpts filesystem is now distinct such that ptys
+and their indices allocated in one mount are independent from ptys
+and their indices in all other mounts.
+
+All mounts of the devpts filesystem now create a ``/dev/pts/ptmx`` node
+with permissions ``0000``.
+
+To retain backwards compatibility the a ptmx device node (aka any node
+created with ``mknod name c 5 2``) when opened will look for an instance
+of devpts under the name ``pts`` in the same directory as the ptmx device
+node.
+
+As an option instead of placing a ``/dev/ptmx`` device node at ``/dev/ptmx``
+it is possible to place a symlink to ``/dev/pts/ptmx`` at ``/dev/ptmx`` or
+to bind mount ``/dev/ptx/ptmx`` to ``/dev/ptmx``.  If you opt for using
+the devpts filesystem in this manner devpts should be mounted with
+the ``ptmxmode=0666``, or ``chmod 0666 /dev/pts/ptmx`` should be called.
+
+Total count of pty pairs in all instances is limited by sysctls::
+
+    kernel.pty.max = 4096	- global limit
+    kernel.pty.reserve = 1024	- reserved for filesystems mounted from the initial mount namespace
+    kernel.pty.nr		- current count of ptys
+
+Per-instance limit could be set by adding mount option ``max=<count>``.
+
+This feature was added in kernel 3.4 together with
+``sysctl kernel.pty.reserve``.
+
+In kernels older than 3.4 sysctl ``kernel.pty.max`` works as per-instance limit.