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, 27 insertions, 0 deletions

diff --git a/Documentation/admin-guide/lcd-panel-cgram.rst b/Documentation/admin-guide/lcd-panel-cgram.rst
new file mode 100644
index 000000000..a3eb00c62
--- /dev/null
+++ b/Documentation/admin-guide/lcd-panel-cgram.rst
@@ -0,0 +1,27 @@
+======================================
+Parallel port LCD/Keypad Panel support
+======================================
+
+Some LCDs allow you to define up to 8 characters, mapped to ASCII
+characters 0 to 7. The escape code to define a new character is
+'\e[LG' followed by one digit from 0 to 7, representing the character
+number, and up to 8 couples of hex digits terminated by a semi-colon
+(';'). Each couple of digits represents a line, with 1-bits for each
+illuminated pixel with LSB on the right. Lines are numbered from the
+top of the character to the bottom. On a 5x7 matrix, only the 5 lower
+bits of the 7 first bytes are used for each character. If the string
+is incomplete, only complete lines will be redefined. Here are some
+examples::
+
+  printf "\e[LG0010101050D1F0C04;"  => 0 = [enter]
+  printf "\e[LG1040E1F0000000000;"  => 1 = [up]
+  printf "\e[LG2000000001F0E0400;"  => 2 = [down]
+  printf "\e[LG3040E1F001F0E0400;"  => 3 = [up-down]
+  printf "\e[LG40002060E1E0E0602;"  => 4 = [left]
+  printf "\e[LG500080C0E0F0E0C08;"  => 5 = [right]
+  printf "\e[LG60016051516141400;"  => 6 = "IP"
+
+  printf "\e[LG00103071F1F070301;"  => big speaker
+  printf "\e[LG00002061E1E060200;"  => small speaker
+
+Willy