Commit aa7d3a56 authored by Chen Ridong's avatar Chen Ridong Committed by Tejun Heo
Browse files

cpuset: fix warning when disabling remote partition



A warning was triggered as follows:

WARNING: kernel/cgroup/cpuset.c:1651 at remote_partition_disable+0xf7/0x110
RIP: 0010:remote_partition_disable+0xf7/0x110
RSP: 0018:ffffc90001947d88 EFLAGS: 00000206
RAX: 0000000000007fff RBX: ffff888103b6e000 RCX: 0000000000006f40
RDX: 0000000000006f00 RSI: ffffc90001947da8 RDI: ffff888103b6e000
RBP: ffff888103b6e000 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000001 R11: ffff88810b2e2728 R12: ffffc90001947da8
R13: 0000000000000000 R14: ffffc90001947da8 R15: ffff8881081f1c00
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f55c8bbe0b2 CR3: 000000010b14c000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 update_prstate+0x2d3/0x580
 cpuset_partition_write+0x94/0xf0
 kernfs_fop_write_iter+0x147/0x200
 vfs_write+0x35d/0x500
 ksys_write+0x66/0xe0
 do_syscall_64+0x6b/0x390
 entry_SYSCALL_64_after_hwframe+0x4b/0x53
RIP: 0033:0x7f55c8cd4887

Reproduction steps (on a 16-CPU machine):

        # cd /sys/fs/cgroup/
        # mkdir A1
        # echo +cpuset > A1/cgroup.subtree_control
        # echo "0-14" > A1/cpuset.cpus.exclusive
        # mkdir A1/A2
        # echo "0-14" > A1/A2/cpuset.cpus.exclusive
        # echo "root" > A1/A2/cpuset.cpus.partition
        # echo 0 > /sys/devices/system/cpu/cpu15/online
        # echo member > A1/A2/cpuset.cpus.partition

When CPU 15 is offlined, subpartitions_cpus gets cleared because no CPUs
remain available for the top_cpuset, forcing partitions to share CPUs with
the top_cpuset. In this scenario, disabling the remote partition triggers
a warning stating that effective_xcpus is not a subset of
subpartitions_cpus. Partitions should be invalidated in this case to
inform users that the partition is now invalid(cpus are shared with
top_cpuset).

To fix this issue:
1. Only emit the warning only if subpartitions_cpus is not empty and the
   effective_xcpus is not a subset of subpartitions_cpus.
2. During the CPU hotplug process, invalidate partitions if
   subpartitions_cpus is empty.

Fixes: f62a5d39 ("cgroup/cpuset: Remove remote_partition_check() & make update_cpumasks_hier() handle remote partition")
Signed-off-by: default avatarChen Ridong <chenridong@huawei.com>
Reviewed-by: default avatarWaiman Long <longman@redhat.com>
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
parent 3309b63a
Loading
Loading
Loading
Loading
+16 −5
Original line number Diff line number Diff line
@@ -1668,7 +1668,14 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
{
	WARN_ON_ONCE(!is_remote_partition(cs));
	WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus));
	/*
	 * When a CPU is offlined, top_cpuset may end up with no available CPUs,
	 * which should clear subpartitions_cpus. We should not emit a warning for this
	 * scenario: the hierarchy is updated from top to bottom, so subpartitions_cpus
	 * may already be cleared when disabling the partition.
	 */
	WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus) &&
		     !cpumask_empty(subpartitions_cpus));

	spin_lock_irq(&callback_lock);
	cs->remote_partition = false;
@@ -3976,8 +3983,9 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
	if (remote || (is_partition_valid(cs) && is_partition_valid(parent)))
		compute_partition_effective_cpumask(cs, &new_cpus);

	if (remote && cpumask_empty(&new_cpus) &&
	    partition_is_populated(cs, NULL)) {
	if (remote && (cpumask_empty(subpartitions_cpus) ||
			(cpumask_empty(&new_cpus) &&
			 partition_is_populated(cs, NULL)))) {
		cs->prs_err = PERR_HOTPLUG;
		remote_partition_disable(cs, tmp);
		compute_effective_cpumask(&new_cpus, cs, parent);
@@ -3990,9 +3998,12 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
	 * 1) empty effective cpus but not valid empty partition.
	 * 2) parent is invalid or doesn't grant any cpus to child
	 *    partitions.
	 * 3) subpartitions_cpus is empty.
	 */
	if (is_local_partition(cs) && (!is_partition_valid(parent) ||
				tasks_nocpu_error(parent, cs, &new_cpus)))
	if (is_local_partition(cs) &&
	    (!is_partition_valid(parent) ||
	     tasks_nocpu_error(parent, cs, &new_cpus) ||
	     cpumask_empty(subpartitions_cpus)))
		partcmd = partcmd_invalidate;
	/*
	 * On the other hand, an invalid partition root may be transitioned