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, 107 insertions, 0 deletions

diff --git a/include/uapi/asm-generic/ioctl.h b/include/uapi/asm-generic/ioctl.h
new file mode 100644
index 000000000..e3290a582
--- /dev/null
+++ b/include/uapi/asm-generic/ioctl.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_ASM_GENERIC_IOCTL_H
+#define _UAPI_ASM_GENERIC_IOCTL_H
+
+/* ioctl command encoding: 32 bits total, command in lower 16 bits,
+ * size of the parameter structure in the lower 14 bits of the
+ * upper 16 bits.
+ * Encoding the size of the parameter structure in the ioctl request
+ * is useful for catching programs compiled with old versions
+ * and to avoid overwriting user space outside the user buffer area.
+ * The highest 2 bits are reserved for indicating the ``access mode''.
+ * NOTE: This limits the max parameter size to 16kB -1 !
+ */
+
+/*
+ * The following is for compatibility across the various Linux
+ * platforms.  The generic ioctl numbering scheme doesn't really enforce
+ * a type field.  De facto, however, the top 8 bits of the lower 16
+ * bits are indeed used as a type field, so we might just as well make
+ * this explicit here.  Please be sure to use the decoding macros
+ * below from now on.
+ */
+#define _IOC_NRBITS	8
+#define _IOC_TYPEBITS	8
+
+/*
+ * Let any architecture override either of the following before
+ * including this file.
+ */
+
+#ifndef _IOC_SIZEBITS
+# define _IOC_SIZEBITS	14
+#endif
+
+#ifndef _IOC_DIRBITS
+# define _IOC_DIRBITS	2
+#endif
+
+#define _IOC_NRMASK	((1 << _IOC_NRBITS)-1)
+#define _IOC_TYPEMASK	((1 << _IOC_TYPEBITS)-1)
+#define _IOC_SIZEMASK	((1 << _IOC_SIZEBITS)-1)
+#define _IOC_DIRMASK	((1 << _IOC_DIRBITS)-1)
+
+#define _IOC_NRSHIFT	0
+#define _IOC_TYPESHIFT	(_IOC_NRSHIFT+_IOC_NRBITS)
+#define _IOC_SIZESHIFT	(_IOC_TYPESHIFT+_IOC_TYPEBITS)
+#define _IOC_DIRSHIFT	(_IOC_SIZESHIFT+_IOC_SIZEBITS)
+
+/*
+ * Direction bits, which any architecture can choose to override
+ * before including this file.
+ *
+ * NOTE: _IOC_WRITE means userland is writing and kernel is
+ * reading. _IOC_READ means userland is reading and kernel is writing.
+ */
+
+#ifndef _IOC_NONE
+# define _IOC_NONE	0U
+#endif
+
+#ifndef _IOC_WRITE
+# define _IOC_WRITE	1U
+#endif
+
+#ifndef _IOC_READ
+# define _IOC_READ	2U
+#endif
+
+#define _IOC(dir,type,nr,size) \
+	(((dir)  << _IOC_DIRSHIFT) | \
+	 ((type) << _IOC_TYPESHIFT) | \
+	 ((nr)   << _IOC_NRSHIFT) | \
+	 ((size) << _IOC_SIZESHIFT))
+
+#ifndef __KERNEL__
+#define _IOC_TYPECHECK(t) (sizeof(t))
+#endif
+
+/*
+ * Used to create numbers.
+ *
+ * NOTE: _IOW means userland is writing and kernel is reading. _IOR
+ * means userland is reading and kernel is writing.
+ */
+#define _IO(type,nr)			_IOC(_IOC_NONE,(type),(nr),0)
+#define _IOR(type,nr,argtype)		_IOC(_IOC_READ,(type),(nr),(_IOC_TYPECHECK(argtype)))
+#define _IOW(type,nr,argtype)		_IOC(_IOC_WRITE,(type),(nr),(_IOC_TYPECHECK(argtype)))
+#define _IOWR(type,nr,argtype)		_IOC(_IOC_READ|_IOC_WRITE,(type),(nr),(_IOC_TYPECHECK(argtype)))
+#define _IOR_BAD(type,nr,argtype)	_IOC(_IOC_READ,(type),(nr),sizeof(argtype))
+#define _IOW_BAD(type,nr,argtype)	_IOC(_IOC_WRITE,(type),(nr),sizeof(argtype))
+#define _IOWR_BAD(type,nr,argtype)	_IOC(_IOC_READ|_IOC_WRITE,(type),(nr),sizeof(argtype))
+
+/* used to decode ioctl numbers.. */
+#define _IOC_DIR(nr)		(((nr) >> _IOC_DIRSHIFT) & _IOC_DIRMASK)
+#define _IOC_TYPE(nr)		(((nr) >> _IOC_TYPESHIFT) & _IOC_TYPEMASK)
+#define _IOC_NR(nr)		(((nr) >> _IOC_NRSHIFT) & _IOC_NRMASK)
+#define _IOC_SIZE(nr)		(((nr) >> _IOC_SIZESHIFT) & _IOC_SIZEMASK)
+
+/* ...and for the drivers/sound files... */
+
+#define IOC_IN		(_IOC_WRITE << _IOC_DIRSHIFT)
+#define IOC_OUT		(_IOC_READ << _IOC_DIRSHIFT)
+#define IOC_INOUT	((_IOC_WRITE|_IOC_READ) << _IOC_DIRSHIFT)
+#define IOCSIZE_MASK	(_IOC_SIZEMASK << _IOC_SIZESHIFT)
+#define IOCSIZE_SHIFT	(_IOC_SIZESHIFT)
+
+#endif /* _UAPI_ASM_GENERIC_IOCTL_H */