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/drivers/net/netdevsim/tc.c b/drivers/net/netdevsim/tc.c
new file mode 100644
index 000000000..a415e02a6
--- /dev/null
+++ b/drivers/net/netdevsim/tc.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/netdevice.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+
+#include "netdevsim.h"
+
+static int
+nsim_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
+{
+	struct flow_cls_common_offload *common = type_data;
+	int err = 0;
+
+	switch (type) {
+	case TC_SETUP_CLSBPF:
+		err = nsim_bpf_setup_tc_block_cb(type, type_data, cb_priv);
+		break;
+	case TC_SETUP_CLSFLOWER:
+		break;
+	default:
+		NSIM_EA(common->extack, "offload type not supported");
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static void nsim_taprio_stats(struct tc_taprio_qopt_stats *stats)
+{
+	stats->window_drops = 0;
+	stats->tx_overruns = 0;
+}
+
+static int nsim_setup_tc_taprio(struct net_device *dev,
+				struct tc_taprio_qopt_offload *offload)
+{
+	int err = 0;
+
+	switch (offload->cmd) {
+	case TAPRIO_CMD_REPLACE:
+	case TAPRIO_CMD_DESTROY:
+		break;
+	case TAPRIO_CMD_STATS:
+		nsim_taprio_stats(&offload->stats);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int nsim_setup_tc_ets(struct net_device *dev,
+			     struct tc_ets_qopt_offload *offload)
+{
+	int err = 0;
+
+	switch (offload->command) {
+	case TC_ETS_REPLACE:
+	case TC_ETS_DESTROY:
+		break;
+	case TC_ETS_STATS:
+		_bstats_update(offload->stats.bstats, 0, 0);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static LIST_HEAD(nsim_block_cb_list);
+
+int
+nsim_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_QDISC_TAPRIO:
+		return nsim_setup_tc_taprio(dev, type_data);
+	case TC_SETUP_QDISC_ETS:
+		return nsim_setup_tc_ets(dev, type_data);
+	case TC_SETUP_BLOCK:
+		return flow_block_cb_setup_simple(type_data,
+						  &nsim_block_cb_list,
+						  nsim_setup_tc_block_cb,
+						  ns, ns, true);
+	case TC_SETUP_FT:
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+ALLOW_ERROR_INJECTION(nsim_setup_tc, ERRNO);