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, 156 insertions, 0 deletions

diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
new file mode 100644
index 000000000..46d9e9b98
--- /dev/null
+++ b/arch/x86/lib/putuser.S
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * __put_user functions.
+ *
+ * (C) Copyright 2005 Linus Torvalds
+ * (C) Copyright 2005 Andi Kleen
+ * (C) Copyright 2008 Glauber Costa
+ *
+ * These functions have a non-standard call interface
+ * to make them more efficient, especially as they
+ * return an error value in addition to the "real"
+ * return value.
+ */
+#include <linux/export.h>
+#include <linux/linkage.h>
+#include <linux/objtool.h>
+#include <asm/thread_info.h>
+#include <asm/errno.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+
+/*
+ * __put_user_X
+ *
+ * Inputs:	%eax[:%edx] contains the data
+ *		%ecx contains the address
+ *
+ * Outputs:	%ecx is error code (0 or -EFAULT)
+ *
+ * Clobbers:	%ebx needed for task pointer
+ *
+ * These functions should not modify any other registers,
+ * as they get called from within inline assembly.
+ */
+
+.macro check_range size:req
+.if IS_ENABLED(CONFIG_X86_64)
+	mov %rcx, %rbx
+	sar $63, %rbx
+	or %rbx, %rcx
+.else
+	cmp $TASK_SIZE_MAX-\size+1, %ecx
+	jae .Lbad_put_user
+.endif
+.endm
+
+.text
+SYM_FUNC_START(__put_user_1)
+	ANNOTATE_NOENDBR
+	check_range size=1
+	ASM_STAC
+1:	movb %al,(%_ASM_CX)
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_1)
+EXPORT_SYMBOL(__put_user_1)
+
+SYM_FUNC_START(__put_user_nocheck_1)
+	ANNOTATE_NOENDBR
+	ASM_STAC
+2:	movb %al,(%_ASM_CX)
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_nocheck_1)
+EXPORT_SYMBOL(__put_user_nocheck_1)
+
+SYM_FUNC_START(__put_user_2)
+	ANNOTATE_NOENDBR
+	check_range size=2
+	ASM_STAC
+3:	movw %ax,(%_ASM_CX)
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_2)
+EXPORT_SYMBOL(__put_user_2)
+
+SYM_FUNC_START(__put_user_nocheck_2)
+	ANNOTATE_NOENDBR
+	ASM_STAC
+4:	movw %ax,(%_ASM_CX)
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_nocheck_2)
+EXPORT_SYMBOL(__put_user_nocheck_2)
+
+SYM_FUNC_START(__put_user_4)
+	ANNOTATE_NOENDBR
+	check_range size=4
+	ASM_STAC
+5:	movl %eax,(%_ASM_CX)
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_4)
+EXPORT_SYMBOL(__put_user_4)
+
+SYM_FUNC_START(__put_user_nocheck_4)
+	ANNOTATE_NOENDBR
+	ASM_STAC
+6:	movl %eax,(%_ASM_CX)
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_nocheck_4)
+EXPORT_SYMBOL(__put_user_nocheck_4)
+
+SYM_FUNC_START(__put_user_8)
+	ANNOTATE_NOENDBR
+	check_range size=8
+	ASM_STAC
+7:	mov %_ASM_AX,(%_ASM_CX)
+#ifdef CONFIG_X86_32
+8:	movl %edx,4(%_ASM_CX)
+#endif
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_8)
+EXPORT_SYMBOL(__put_user_8)
+
+SYM_FUNC_START(__put_user_nocheck_8)
+	ANNOTATE_NOENDBR
+	ASM_STAC
+9:	mov %_ASM_AX,(%_ASM_CX)
+#ifdef CONFIG_X86_32
+10:	movl %edx,4(%_ASM_CX)
+#endif
+	xor %ecx,%ecx
+	ASM_CLAC
+	RET
+SYM_FUNC_END(__put_user_nocheck_8)
+EXPORT_SYMBOL(__put_user_nocheck_8)
+
+SYM_CODE_START_LOCAL(__put_user_handle_exception)
+	ASM_CLAC
+.Lbad_put_user:
+	movl $-EFAULT,%ecx
+	RET
+SYM_CODE_END(__put_user_handle_exception)
+
+	_ASM_EXTABLE_UA(1b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(2b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(3b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(4b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(5b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(6b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(7b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(9b, __put_user_handle_exception)
+#ifdef CONFIG_X86_32
+	_ASM_EXTABLE_UA(8b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(10b, __put_user_handle_exception)
+#endif