From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug 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 Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- drivers/net/team/Kconfig | 77 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) create mode 100644 drivers/net/team/Kconfig (limited to 'drivers/net/team/Kconfig') diff --git a/drivers/net/team/Kconfig b/drivers/net/team/Kconfig new file mode 100644 index 000000000..4d449845d --- /dev/null +++ b/drivers/net/team/Kconfig @@ -0,0 +1,77 @@ +# SPDX-License-Identifier: GPL-2.0-only +menuconfig NET_TEAM + tristate "Ethernet team driver support" + help + This allows one to create virtual interfaces that teams together + multiple ethernet devices. + + Team devices can be added using the "ip" command from the + iproute2 package: + + "ip link add link [ address MAC ] [ NAME ] type team" + + To compile this driver as a module, choose M here: the module + will be called team. + +if NET_TEAM + +config NET_TEAM_MODE_BROADCAST + tristate "Broadcast mode support" + depends on NET_TEAM + help + Basic mode where packets are transmitted always by all suitable ports. + + All added ports are setup to have team's device address. + + To compile this team mode as a module, choose M here: the module + will be called team_mode_broadcast. + +config NET_TEAM_MODE_ROUNDROBIN + tristate "Round-robin mode support" + depends on NET_TEAM + help + Basic mode where port used for transmitting packets is selected in + round-robin fashion using packet counter. + + All added ports are setup to have team's device address. + + To compile this team mode as a module, choose M here: the module + will be called team_mode_roundrobin. + +config NET_TEAM_MODE_RANDOM + tristate "Random mode support" + depends on NET_TEAM + help + Basic mode where port used for transmitting packets is selected + randomly. + + All added ports are setup to have team's device address. + + To compile this team mode as a module, choose M here: the module + will be called team_mode_random. + +config NET_TEAM_MODE_ACTIVEBACKUP + tristate "Active-backup mode support" + depends on NET_TEAM + help + Only one port is active at a time and the rest of ports are used + for backup. + + Mac addresses of ports are not modified. Userspace is responsible + to do so. + + To compile this team mode as a module, choose M here: the module + will be called team_mode_activebackup. + +config NET_TEAM_MODE_LOADBALANCE + tristate "Load-balance mode support" + depends on NET_TEAM + help + This mode provides load balancing functionality. Tx port selection + is done using BPF function set up from userspace (bpf_hash_func + option) + + To compile this team mode as a module, choose M here: the module + will be called team_mode_loadbalance. + +endif # NET_TEAM -- cgit v1.3.1