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, 336 insertions, 0 deletions

diff --git a/scripts/atomic/gen-atomic-fallback.sh b/scripts/atomic/gen-atomic-fallback.sh
new file mode 100755
index 000000000..f80d69cfe
--- /dev/null
+++ b/scripts/atomic/gen-atomic-fallback.sh
@@ -0,0 +1,336 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+ATOMICDIR=$(dirname $0)
+
+. ${ATOMICDIR}/atomic-tbl.sh
+
+#gen_template_fallback(template, meta, pfx, name, sfx, order, atomic, int, args...)
+gen_template_fallback()
+{
+	local template="$1"; shift
+	local meta="$1"; shift
+	local pfx="$1"; shift
+	local name="$1"; shift
+	local sfx="$1"; shift
+	local order="$1"; shift
+	local atomic="$1"; shift
+	local int="$1"; shift
+
+	local ret="$(gen_ret_type "${meta}" "${int}")"
+	local retstmt="$(gen_ret_stmt "${meta}")"
+	local params="$(gen_params "${int}" "${atomic}" "$@")"
+	local args="$(gen_args "$@")"
+
+	. ${template}
+}
+
+#gen_order_fallback(meta, pfx, name, sfx, order, atomic, int, args...)
+gen_order_fallback()
+{
+	local meta="$1"; shift
+	local pfx="$1"; shift
+	local name="$1"; shift
+	local sfx="$1"; shift
+	local order="$1"; shift
+
+	local tmpl_order=${order#_}
+	local tmpl="${ATOMICDIR}/fallbacks/${tmpl_order:-fence}"
+	gen_template_fallback "${tmpl}" "${meta}" "${pfx}" "${name}" "${sfx}" "${order}" "$@"
+}
+
+#gen_proto_fallback(meta, pfx, name, sfx, order, atomic, int, args...)
+gen_proto_fallback()
+{
+	local meta="$1"; shift
+	local pfx="$1"; shift
+	local name="$1"; shift
+	local sfx="$1"; shift
+	local order="$1"; shift
+
+	local tmpl="$(find_fallback_template "${pfx}" "${name}" "${sfx}" "${order}")"
+	gen_template_fallback "${tmpl}" "${meta}" "${pfx}" "${name}" "${sfx}" "${order}" "$@"
+}
+
+#gen_proto_order_variant(meta, pfx, name, sfx, order, atomic, int, args...)
+gen_proto_order_variant()
+{
+	local meta="$1"; shift
+	local pfx="$1"; shift
+	local name="$1"; shift
+	local sfx="$1"; shift
+	local order="$1"; shift
+	local atomic="$1"; shift
+	local int="$1"; shift
+
+	local atomicname="${atomic}_${pfx}${name}${sfx}${order}"
+	local basename="${atomic}_${pfx}${name}${sfx}"
+
+	local template="$(find_fallback_template "${pfx}" "${name}" "${sfx}" "${order}")"
+
+	local ret="$(gen_ret_type "${meta}" "${int}")"
+	local retstmt="$(gen_ret_stmt "${meta}")"
+	local params="$(gen_params "${int}" "${atomic}" "$@")"
+	local args="$(gen_args "$@")"
+
+	gen_kerneldoc "raw_" "${meta}" "${pfx}" "${name}" "${sfx}" "${order}" "${atomic}" "${int}" "$@"
+
+	printf "static __always_inline ${ret}\n"
+	printf "raw_${atomicname}(${params})\n"
+	printf "{\n"
+
+	# Where there is no possible fallback, this order variant is mandatory
+	# and must be provided by arch code. Add a comment to the header to
+	# make this obvious.
+	#
+	# Ideally we'd error on a missing definition, but arch code might
+	# define this order variant as a C function without a preprocessor
+	# symbol.
+	if [ -z ${template} ] && [ -z "${order}" ] && ! meta_has_relaxed "${meta}"; then
+		printf "\t${retstmt}arch_${atomicname}(${args});\n"
+		printf "}\n\n"
+		return
+	fi
+
+	printf "#if defined(arch_${atomicname})\n"
+	printf "\t${retstmt}arch_${atomicname}(${args});\n"
+
+	# Allow FULL/ACQUIRE/RELEASE ops to be defined in terms of RELAXED ops
+	if [ "${order}" != "_relaxed" ] && meta_has_relaxed "${meta}"; then
+		printf "#elif defined(arch_${basename}_relaxed)\n"
+		gen_order_fallback "${meta}" "${pfx}" "${name}" "${sfx}" "${order}" "${atomic}" "${int}" "$@"
+	fi
+
+	# Allow ACQUIRE/RELEASE/RELAXED ops to be defined in terms of FULL ops
+	if [ ! -z "${order}" ] && ! meta_is_implicitly_relaxed "${meta}"; then
+		printf "#elif defined(arch_${basename})\n"
+		printf "\t${retstmt}arch_${basename}(${args});\n"
+	fi
+
+	printf "#else\n"
+	if [ ! -z "${template}" ]; then
+		gen_proto_fallback "${meta}" "${pfx}" "${name}" "${sfx}" "${order}" "${atomic}" "${int}" "$@"
+	else
+		printf "#error \"Unable to define raw_${atomicname}\"\n"
+	fi
+
+	printf "#endif\n"
+	printf "}\n\n"
+}
+
+
+#gen_proto_order_variants(meta, pfx, name, sfx, atomic, int, args...)
+gen_proto_order_variants()
+{
+	local meta="$1"; shift
+	local pfx="$1"; shift
+	local name="$1"; shift
+	local sfx="$1"; shift
+	local atomic="$1"
+
+	gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "" "$@"
+
+	if meta_has_acquire "${meta}"; then
+		gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_acquire" "$@"
+	fi
+
+	if meta_has_release "${meta}"; then
+		gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_release" "$@"
+	fi
+
+	if meta_has_relaxed "${meta}"; then
+		gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_relaxed" "$@"
+	fi
+}
+
+#gen_basic_fallbacks(basename)
+gen_basic_fallbacks()
+{
+	local basename="$1"; shift
+cat << EOF
+#define raw_${basename}_acquire arch_${basename}
+#define raw_${basename}_release arch_${basename}
+#define raw_${basename}_relaxed arch_${basename}
+EOF
+}
+
+gen_order_fallbacks()
+{
+	local xchg="$1"; shift
+
+cat <<EOF
+
+#define raw_${xchg}_relaxed arch_${xchg}_relaxed
+
+#ifdef arch_${xchg}_acquire
+#define raw_${xchg}_acquire arch_${xchg}_acquire
+#else
+#define raw_${xchg}_acquire(...) \\
+	__atomic_op_acquire(arch_${xchg}, __VA_ARGS__)
+#endif
+
+#ifdef arch_${xchg}_release
+#define raw_${xchg}_release arch_${xchg}_release
+#else
+#define raw_${xchg}_release(...) \\
+	__atomic_op_release(arch_${xchg}, __VA_ARGS__)
+#endif
+
+#ifdef arch_${xchg}
+#define raw_${xchg} arch_${xchg}
+#else
+#define raw_${xchg}(...) \\
+	__atomic_op_fence(arch_${xchg}, __VA_ARGS__)
+#endif
+
+EOF
+}
+
+gen_xchg_order_fallback()
+{
+	local xchg="$1"; shift
+	local order="$1"; shift
+	local forder="${order:-_fence}"
+
+	printf "#if defined(arch_${xchg}${order})\n"
+	printf "#define raw_${xchg}${order} arch_${xchg}${order}\n"
+
+	if [ "${order}" != "_relaxed" ]; then
+		printf "#elif defined(arch_${xchg}_relaxed)\n"
+		printf "#define raw_${xchg}${order}(...) \\\\\n"
+		printf "	__atomic_op${forder}(arch_${xchg}, __VA_ARGS__)\n"
+	fi
+
+	if [ ! -z "${order}" ]; then
+		printf "#elif defined(arch_${xchg})\n"
+		printf "#define raw_${xchg}${order} arch_${xchg}\n"
+	fi
+
+	printf "#else\n"
+	printf "extern void raw_${xchg}${order}_not_implemented(void);\n"
+	printf "#define raw_${xchg}${order}(...) raw_${xchg}${order}_not_implemented()\n"
+	printf "#endif\n\n"
+}
+
+gen_xchg_fallbacks()
+{
+	local xchg="$1"; shift
+
+	for order in "" "_acquire" "_release" "_relaxed"; do
+		gen_xchg_order_fallback "${xchg}" "${order}"
+	done
+}
+
+gen_try_cmpxchg_fallback()
+{
+	local prefix="$1"; shift
+	local cmpxchg="$1"; shift;
+	local suffix="$1"; shift;
+
+cat <<EOF
+#define raw_${prefix}try_${cmpxchg}${suffix}(_ptr, _oldp, _new) \\
+({ \\
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \\
+	___r = raw_${prefix}${cmpxchg}${suffix}((_ptr), ___o, (_new)); \\
+	if (unlikely(___r != ___o)) \\
+		*___op = ___r; \\
+	likely(___r == ___o); \\
+})
+EOF
+}
+
+gen_try_cmpxchg_order_fallback()
+{
+	local cmpxchg="$1"; shift
+	local order="$1"; shift
+	local forder="${order:-_fence}"
+
+	printf "#if defined(arch_try_${cmpxchg}${order})\n"
+	printf "#define raw_try_${cmpxchg}${order} arch_try_${cmpxchg}${order}\n"
+
+	if [ "${order}" != "_relaxed" ]; then
+		printf "#elif defined(arch_try_${cmpxchg}_relaxed)\n"
+		printf "#define raw_try_${cmpxchg}${order}(...) \\\\\n"
+		printf "	__atomic_op${forder}(arch_try_${cmpxchg}, __VA_ARGS__)\n"
+	fi
+
+	if [ ! -z "${order}" ]; then
+		printf "#elif defined(arch_try_${cmpxchg})\n"
+		printf "#define raw_try_${cmpxchg}${order} arch_try_${cmpxchg}\n"
+	fi
+
+	printf "#else\n"
+	gen_try_cmpxchg_fallback "" "${cmpxchg}" "${order}"
+	printf "#endif\n\n"
+}
+
+gen_try_cmpxchg_order_fallbacks()
+{
+	local cmpxchg="$1"; shift;
+
+	for order in "" "_acquire" "_release" "_relaxed"; do
+		gen_try_cmpxchg_order_fallback "${cmpxchg}" "${order}"
+	done
+}
+
+gen_def_and_try_cmpxchg_fallback()
+{
+	local prefix="$1"; shift
+	local cmpxchg="$1"; shift
+	local suffix="$1"; shift
+
+	printf "#define raw_${prefix}${cmpxchg}${suffix} arch_${prefix}${cmpxchg}${suffix}\n\n"
+	printf "#ifdef arch_${prefix}try_${cmpxchg}${suffix}\n"
+	printf "#define raw_${prefix}try_${cmpxchg}${suffix} arch_${prefix}try_${cmpxchg}${suffix}\n"
+	printf "#else\n"
+	gen_try_cmpxchg_fallback "${prefix}" "${cmpxchg}" "${suffix}"
+	printf "#endif\n\n"
+}
+
+cat << EOF
+// SPDX-License-Identifier: GPL-2.0
+
+// Generated by $0
+// DO NOT MODIFY THIS FILE DIRECTLY
+
+#ifndef _LINUX_ATOMIC_FALLBACK_H
+#define _LINUX_ATOMIC_FALLBACK_H
+
+#include <linux/compiler.h>
+
+EOF
+
+for xchg in "xchg" "cmpxchg" "cmpxchg64" "cmpxchg128"; do
+	gen_xchg_fallbacks "${xchg}"
+done
+
+for cmpxchg in "cmpxchg" "cmpxchg64" "cmpxchg128"; do
+	gen_try_cmpxchg_order_fallbacks "${cmpxchg}"
+done
+
+for cmpxchg in "cmpxchg" "cmpxchg64" "cmpxchg128"; do
+	gen_def_and_try_cmpxchg_fallback "" "${cmpxchg}" "_local"
+done
+
+for cmpxchg in "cmpxchg"; do
+	gen_def_and_try_cmpxchg_fallback "sync_" "${cmpxchg}" ""
+done
+
+grep '^[a-z]' "$1" | while read name meta args; do
+	gen_proto "${meta}" "${name}" "atomic" "int" ${args}
+done
+
+cat <<EOF
+#ifdef CONFIG_GENERIC_ATOMIC64
+#include <asm-generic/atomic64.h>
+#endif
+
+EOF
+
+grep '^[a-z]' "$1" | while read name meta args; do
+	gen_proto "${meta}" "${name}" "atomic64" "s64" ${args}
+done
+
+cat <<EOF
+#endif /* _LINUX_ATOMIC_FALLBACK_H */
+EOF