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, 97 insertions, 0 deletions

diff --git a/net/sunrpc/netlink.c b/net/sunrpc/netlink.c
new file mode 100644
index 000000000..ce09ecc0f
--- /dev/null
+++ b/net/sunrpc/netlink.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/sunrpc_cache.yaml */
+/* YNL-GEN kernel source */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "netlink.h"
+
+#include <uapi/linux/sunrpc_netlink.h>
+
+/* Common nested types */
+const struct nla_policy sunrpc_ip_map_nl_policy[SUNRPC_A_IP_MAP_EXPIRY + 1] = {
+	[SUNRPC_A_IP_MAP_SEQNO] = { .type = NLA_U64, },
+	[SUNRPC_A_IP_MAP_CLASS] = { .type = NLA_NUL_STRING, },
+	[SUNRPC_A_IP_MAP_ADDR] = { .type = NLA_NUL_STRING, },
+	[SUNRPC_A_IP_MAP_DOMAIN] = { .type = NLA_NUL_STRING, },
+	[SUNRPC_A_IP_MAP_NEGATIVE] = { .type = NLA_FLAG, },
+	[SUNRPC_A_IP_MAP_EXPIRY] = { .type = NLA_U64, },
+};
+
+const struct nla_policy sunrpc_unix_gid_nl_policy[SUNRPC_A_UNIX_GID_EXPIRY + 1] = {
+	[SUNRPC_A_UNIX_GID_SEQNO] = { .type = NLA_U64, },
+	[SUNRPC_A_UNIX_GID_UID] = { .type = NLA_U32, },
+	[SUNRPC_A_UNIX_GID_GIDS] = { .type = NLA_U32, },
+	[SUNRPC_A_UNIX_GID_NEGATIVE] = { .type = NLA_FLAG, },
+	[SUNRPC_A_UNIX_GID_EXPIRY] = { .type = NLA_U64, },
+};
+
+/* SUNRPC_CMD_IP_MAP_SET_REQS - do */
+static const struct nla_policy sunrpc_ip_map_set_reqs_nl_policy[SUNRPC_A_IP_MAP_REQS_REQUESTS + 1] = {
+	[SUNRPC_A_IP_MAP_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_ip_map_nl_policy),
+};
+
+/* SUNRPC_CMD_UNIX_GID_SET_REQS - do */
+static const struct nla_policy sunrpc_unix_gid_set_reqs_nl_policy[SUNRPC_A_UNIX_GID_REQS_REQUESTS + 1] = {
+	[SUNRPC_A_UNIX_GID_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_unix_gid_nl_policy),
+};
+
+/* SUNRPC_CMD_CACHE_FLUSH - do */
+static const struct nla_policy sunrpc_cache_flush_nl_policy[SUNRPC_A_CACHE_FLUSH_MASK + 1] = {
+	[SUNRPC_A_CACHE_FLUSH_MASK] = NLA_POLICY_MASK(NLA_U32, 0x3),
+};
+
+/* Ops table for sunrpc */
+static const struct genl_split_ops sunrpc_nl_ops[] = {
+	{
+		.cmd	= SUNRPC_CMD_IP_MAP_GET_REQS,
+		.dumpit	= sunrpc_nl_ip_map_get_reqs_dumpit,
+		.flags	= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= SUNRPC_CMD_IP_MAP_SET_REQS,
+		.doit		= sunrpc_nl_ip_map_set_reqs_doit,
+		.policy		= sunrpc_ip_map_set_reqs_nl_policy,
+		.maxattr	= SUNRPC_A_IP_MAP_REQS_REQUESTS,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= SUNRPC_CMD_UNIX_GID_GET_REQS,
+		.dumpit	= sunrpc_nl_unix_gid_get_reqs_dumpit,
+		.flags	= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= SUNRPC_CMD_UNIX_GID_SET_REQS,
+		.doit		= sunrpc_nl_unix_gid_set_reqs_doit,
+		.policy		= sunrpc_unix_gid_set_reqs_nl_policy,
+		.maxattr	= SUNRPC_A_UNIX_GID_REQS_REQUESTS,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= SUNRPC_CMD_CACHE_FLUSH,
+		.doit		= sunrpc_nl_cache_flush_doit,
+		.policy		= sunrpc_cache_flush_nl_policy,
+		.maxattr	= SUNRPC_A_CACHE_FLUSH_MASK,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+};
+
+static const struct genl_multicast_group sunrpc_nl_mcgrps[] = {
+	[SUNRPC_NLGRP_NONE] = { "none", },
+	[SUNRPC_NLGRP_EXPORTD] = { "exportd", },
+};
+
+struct genl_family sunrpc_nl_family __ro_after_init = {
+	.name		= SUNRPC_FAMILY_NAME,
+	.version	= SUNRPC_FAMILY_VERSION,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.module		= THIS_MODULE,
+	.split_ops	= sunrpc_nl_ops,
+	.n_split_ops	= ARRAY_SIZE(sunrpc_nl_ops),
+	.mcgrps		= sunrpc_nl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(sunrpc_nl_mcgrps),
+};