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, 160 insertions, 0 deletions

diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h
new file mode 100644
index 000000000..a70e0e476
--- /dev/null
+++ b/net/devlink/netlink_gen.h
@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/devlink.yaml */
+/* YNL-GEN kernel header */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
+
+#ifndef _LINUX_DEVLINK_GEN_H
+#define _LINUX_DEVLINK_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/devlink.h>
+
+/* Common nested types */
+extern const struct nla_policy devlink_dl_parent_dev_nl_policy[DEVLINK_ATTR_INDEX + 1];
+extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1];
+extern const struct nla_policy devlink_dl_rate_tc_bws_nl_policy[DEVLINK_RATE_TC_ATTR_BW + 1];
+extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1];
+
+/* Ops table for devlink */
+extern const struct genl_split_ops devlink_nl_ops[75];
+
+int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+			struct genl_info *info);
+int devlink_nl_pre_doit_port(const struct genl_split_ops *ops,
+			     struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
+				      struct sk_buff *skb,
+				      struct genl_info *info);
+int devlink_nl_pre_doit_dev_lock(const struct genl_split_ops *ops,
+				 struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_pre_doit_parent_dev_optional(const struct genl_split_ops *ops,
+					    struct sk_buff *skb,
+					    struct genl_info *info);
+void
+devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+		     struct genl_info *info);
+void
+devlink_nl_post_doit_dev_lock(const struct genl_split_ops *ops,
+			      struct sk_buff *skb, struct genl_info *info);
+void
+devlink_nl_post_doit_parent_dev_optional(const struct genl_split_ops *ops,
+					 struct sk_buff *skb,
+					 struct genl_info *info);
+
+int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int devlink_nl_port_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_del_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_split_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_unsplit_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb);
+int devlink_nl_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb);
+int devlink_nl_sb_port_pool_set_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb);
+int devlink_nl_sb_tc_pool_bind_set_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_sb_occ_snapshot_doit(struct sk_buff *skb,
+				    struct genl_info *info);
+int devlink_nl_sb_occ_max_clear_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_dpipe_table_get_doit(struct sk_buff *skb,
+				    struct genl_info *info);
+int devlink_nl_dpipe_entries_get_doit(struct sk_buff *skb,
+				      struct genl_info *info);
+int devlink_nl_dpipe_headers_get_doit(struct sk_buff *skb,
+				      struct genl_info *info);
+int devlink_nl_dpipe_table_counters_set_doit(struct sk_buff *skb,
+					     struct genl_info *info);
+int devlink_nl_resource_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_resource_dump_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_resource_dump_dumpit(struct sk_buff *skb,
+				    struct netlink_callback *cb);
+int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_param_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_param_get_dumpit(struct sk_buff *skb,
+				struct netlink_callback *cb);
+int devlink_nl_param_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb);
+int devlink_nl_region_new_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_del_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_read_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb);
+int devlink_nl_port_param_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_param_get_dumpit(struct sk_buff *skb,
+				     struct netlink_callback *cb);
+int devlink_nl_port_param_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_info_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int devlink_nl_health_reporter_get_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb);
+int devlink_nl_health_reporter_set_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_health_reporter_recover_doit(struct sk_buff *skb,
+					    struct genl_info *info);
+int devlink_nl_health_reporter_diagnose_doit(struct sk_buff *skb,
+					     struct genl_info *info);
+int devlink_nl_health_reporter_dump_get_dumpit(struct sk_buff *skb,
+					       struct netlink_callback *cb);
+int devlink_nl_health_reporter_dump_clear_doit(struct sk_buff *skb,
+					       struct genl_info *info);
+int devlink_nl_flash_update_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int devlink_nl_trap_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb,
+				     struct netlink_callback *cb);
+int devlink_nl_trap_group_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_policer_get_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb);
+int devlink_nl_trap_policer_set_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_health_reporter_test_doit(struct sk_buff *skb,
+					 struct genl_info *info);
+int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_rate_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int devlink_nl_rate_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_rate_new_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_rate_del_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_linecard_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb);
+int devlink_nl_linecard_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_selftests_get_dumpit(struct sk_buff *skb,
+				    struct netlink_callback *cb);
+int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_notify_filter_set_doit(struct sk_buff *skb,
+				      struct genl_info *info);
+
+#endif /* _LINUX_DEVLINK_GEN_H */