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, 77 insertions, 0 deletions

diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
new file mode 100644
index 000000000..06e21c26b
--- /dev/null
+++ b/net/ipv4/Makefile
@@ -0,0 +1,77 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the Linux TCP/IP (INET) layer.
+#
+
+obj-y     := route.o inetpeer.o protocol.o \
+	     ip_input.o ip_fragment.o ip_forward.o ip_options.o \
+	     ip_output.o ip_sockglue.o inet_hashtables.o \
+	     inet_timewait_sock.o inet_connection_sock.o \
+	     tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
+	     tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \
+	     tcp_recovery.o tcp_ulp.o \
+	     tcp_offload.o tcp_plb.o datagram.o raw.o udp.o \
+	     udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
+	     fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
+	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
+	     metrics.o netlink.o nexthop.o udp_tunnel_stub.o
+
+obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
+obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
+obj-$(CONFIG_PROC_FS) += proc.o
+obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
+obj-$(CONFIG_IP_MROUTE) += ipmr.o
+obj-$(CONFIG_IP_MROUTE_COMMON) += ipmr_base.o
+obj-$(CONFIG_NET_IPIP) += ipip.o
+gre-y := gre_demux.o
+fou-y := fou_core.o fou_nl.o fou_bpf.o
+obj-$(CONFIG_NET_FOU) += fou.o
+obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o
+obj-$(CONFIG_NET_IPGRE) += ip_gre.o
+udp_tunnel-y := udp_tunnel_core.o udp_tunnel_nic.o
+obj-$(CONFIG_NET_UDP_TUNNEL) += udp_tunnel.o
+obj-$(CONFIG_NET_IPVTI) += ip_vti.o
+obj-$(CONFIG_SYN_COOKIES) += syncookies.o
+obj-$(CONFIG_INET_AH) += ah4.o
+obj-$(CONFIG_INET_ESP) += esp4.o
+obj-$(CONFIG_INET_ESP_OFFLOAD) += esp4_offload.o
+obj-$(CONFIG_INET_IPCOMP) += ipcomp.o
+obj-$(CONFIG_INET_XFRM_TUNNEL) += xfrm4_tunnel.o
+obj-$(CONFIG_INET_TUNNEL) += tunnel4.o
+obj-$(CONFIG_IP_PNP) += ipconfig.o
+obj-$(CONFIG_NETFILTER)	+= netfilter.o netfilter/
+obj-$(CONFIG_INET_DIAG) += inet_diag.o
+obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
+obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
+obj-$(CONFIG_INET_RAW_DIAG) += raw_diag.o
+obj-$(CONFIG_TCP_CONG_BBR) += tcp_bbr.o
+obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
+obj-$(CONFIG_TCP_CONG_CDG) += tcp_cdg.o
+obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o
+obj-$(CONFIG_TCP_CONG_DCTCP) += tcp_dctcp.o
+obj-$(CONFIG_TCP_CONG_WESTWOOD) += tcp_westwood.o
+obj-$(CONFIG_TCP_CONG_HSTCP) += tcp_highspeed.o
+obj-$(CONFIG_TCP_CONG_HYBLA) += tcp_hybla.o
+obj-$(CONFIG_TCP_CONG_HTCP) += tcp_htcp.o
+obj-$(CONFIG_TCP_CONG_VEGAS) += tcp_vegas.o
+obj-$(CONFIG_TCP_CONG_NV) += tcp_nv.o
+obj-$(CONFIG_TCP_CONG_VENO) += tcp_veno.o
+obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
+obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
+obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
+obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
+obj-$(CONFIG_NET_SOCK_MSG) += tcp_bpf.o
+obj-$(CONFIG_BPF_SYSCALL) += udp_bpf.o
+obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
+
+obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
+		      xfrm4_output.o xfrm4_protocol.o
+obj-$(CONFIG_TCP_AO) += tcp_ao.o
+
+ifeq ($(CONFIG_BPF_JIT),y)
+obj-$(CONFIG_BPF_SYSCALL) += bpf_tcp_ca.o
+endif
+
+ifdef CONFIG_GCOV_PROFILE_NETFILTER
+GCOV_PROFILE_netfilter.o := y
+endif