From db27a748a399e24af715c54c12a7e928e32d15b0 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 19 Oct 2026 14:10:16 -0400 Subject: [PATCH] cgroup/cpuset: Properly disabling partition when partition state switching fails Before commit 103b08709e8a ("cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping"), the partition state can be freely switched from "root" to "isolated" and vice versa. After that commit, the switch from "root" to "isolated" can fail if it exhausts all the housekeeping CPUs. Later on, the switch from "isolated" to "root" can also fail if some of the partition CPUs are boot-time isolated by "isolcpus". A local or remote partition is made invalid when the switch fails. However there are 2 problems with the existing invalidation code. 1) Both the subpartitions_cpus and isolated_cpus are not properly updated. 2) In the case of remote partition with remote_partition flag set, it is not cleared. Fix this by calling the proper partition disabling function in this case. On an x86 test system with boot option "isolcpus=10 cgroup_debug" set and more than 16 cores, the following commands were executed after boot. # cd /sys/fs/cgroup # echo +cpuset > cgroup.subtree_control # cat cpuset.cpus.isolated 10 # mkdir A # echo 10-12 > A/cpuset.cpus # echo isolated > A/cpuset.cpus.partition # cat A/cpuset.cpus.partition isolated Before the patch: # echo root > A/cpuset.cpus.partition # cat A/cpuset.cpus.partition root invalid (partition config conflicts with housekeeping setup) # cat cpuset.cpus.isolated .__DEBUG__.cpuset.cpus.subpartitions 10-12 10-12 After the patch: # echo root > A/cpuset.cpus.partition # cat A/cpuset.cpus.partition root invalid (partition config conflicts with housekeeping setup) # cat cpuset.cpus.isolated .__DEBUG__.cpuset.cpus.subpartitions 10 Reported-by: Tejun Heo Link: https://lore.kernel.org/lkml/7f4c57b26ad120ab30adf35653f1dd94@kernel.org/ Fixes: 4a74e418881f ("cgroup/cpuset: Check partition conflict with housekeeping setup") Fixes: 103b08709e8a ("cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping") Reviewed-by: Guopeng Zhang Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index b8a721bbe50d..3bbff02d5be1 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2928,6 +2928,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask; bool isolcpus_updated = false; + bool disable_partition = false; if (old_prs == new_prs) return 0; @@ -2984,15 +2985,21 @@ static int update_prstate(struct cpuset *cs, int new_prs) * Need to update isolated_cpus. */ if (prstate_housekeeping_conflict(new_prs, parent_prs, - cs->effective_xcpus, NULL)) + cs->effective_xcpus, NULL)) { + disable_partition = true; err = PERR_HKEEPING; - else + } else { isolcpus_updated = true; + } } else { /* * Switching back to member is always allowed even if it * disables child partitions. */ + disable_partition = true; + } + + if (disable_partition) { if (is_remote_partition(cs)) remote_partition_disable(cs, &tmpmask); else @@ -3001,7 +3008,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) /* * Invalidation of child partitions will be done in - * update_cpumasks_hier(). + * update_cpumasks_hier() below. */ } out: @@ -3020,8 +3027,8 @@ static int update_prstate(struct cpuset *cs, int new_prs) isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus); spin_unlock_irq(&callback_lock); - /* Force update if switching back to member & update effective_xcpus */ - update_cpumasks_hier(cs, &tmpmask, !new_prs); + /* Force update if partition is disabled & update effective_xcpus */ + update_cpumasks_hier(cs, &tmpmask, disable_partition); /* A newly created partition must have effective_xcpus set */ WARN_ON_ONCE(!old_prs && (new_prs > 0)