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, 90 insertions, 0 deletions

diff --git a/drivers/video/fbdev/bt455.h b/drivers/video/fbdev/bt455.h
new file mode 100644
index 000000000..dd1404b40
--- /dev/null
+++ b/drivers/video/fbdev/bt455.h
@@ -0,0 +1,90 @@
+/*
+ *	linux/drivers/video/bt455.h
+ *
+ *	Copyright 2003  Thiemo Seufer <seufer@csv.ica.uni-stuttgart.de>
+ *	Copyright 2016  Maciej W. Rozycki <macro@linux-mips.org>
+ *
+ *	This file is subject to the terms and conditions of the GNU General
+ *	Public License. See the file COPYING in the main directory of this
+ *	archive for more details.
+ */
+#include <linux/types.h>
+
+/*
+ * Bt455 byte-wide registers, 32-bit aligned.
+ */
+struct bt455_regs {
+	volatile u8 addr_cmap;
+	u8 pad0[3];
+	volatile u8 addr_cmap_data;
+	u8 pad1[3];
+	volatile u8 addr_clr;
+	u8 pad2[3];
+	volatile u8 addr_ovly;
+	u8 pad3[3];
+};
+
+static inline void bt455_select_reg(struct bt455_regs *regs, int ir)
+{
+	mb();
+	regs->addr_cmap = ir & 0x0f;
+}
+
+static inline void bt455_reset_reg(struct bt455_regs *regs)
+{
+	mb();
+	regs->addr_clr = 0;
+}
+
+/*
+ * Read/write to a Bt455 color map register.
+ */
+static inline void bt455_read_cmap_next(struct bt455_regs *regs, u8 *grey)
+{
+	mb();
+	regs->addr_cmap_data;
+	rmb();
+	*grey = regs->addr_cmap_data & 0xf;
+	rmb();
+	regs->addr_cmap_data;
+}
+
+static inline void bt455_write_cmap_next(struct bt455_regs *regs, u8 grey)
+{
+	wmb();
+	regs->addr_cmap_data = 0x0;
+	wmb();
+	regs->addr_cmap_data = grey & 0xf;
+	wmb();
+	regs->addr_cmap_data = 0x0;
+}
+
+static inline void bt455_write_ovly_next(struct bt455_regs *regs, u8 grey)
+{
+	wmb();
+	regs->addr_ovly = 0x0;
+	wmb();
+	regs->addr_ovly = grey & 0xf;
+	wmb();
+	regs->addr_ovly = 0x0;
+}
+
+static inline void bt455_read_cmap_entry(struct bt455_regs *regs,
+					 int cr, u8 *grey)
+{
+	bt455_select_reg(regs, cr);
+	bt455_read_cmap_next(regs, grey);
+}
+
+static inline void bt455_write_cmap_entry(struct bt455_regs *regs,
+					  int cr, u8 grey)
+{
+	bt455_select_reg(regs, cr);
+	bt455_write_cmap_next(regs, grey);
+}
+
+static inline void bt455_write_ovly_entry(struct bt455_regs *regs, u8 grey)
+{
+	bt455_reset_reg(regs);
+	bt455_write_ovly_next(regs, grey);
+}