Re: [PATCH v2 1/3] cgroup/cpuset: Fix incorrect CPU accounting with parent's effective_xcpus expansion

[Guopeng Zhang]

在 2026/10/31 03:06, Waiman Long 写道:
> Commit ec0254b9eb49 ("cgroup/cpuset: Release invalid isolated CPUs with
> a shrunk root partition parent") fixes incorrect isolated_cpus accounting
> when contraction of a parent's effective_xcpus can cause a child partition
> to lose isolated CPUs. Expansion of parent's effective_cpus can also allow
> a child partition to gain more effective_xcpus. However, the current code
> doesn't handle this case correctly leading to incorrect effective_cpus
> and isolated_cpus accounting. Fix that by looking for this possible
> expansion of effective_xcpus and perform the proper accounting action.
> 
> New test cases are added to test this effective_xcpus expansion scenarios.
> 
> Reported-by: Guopeng Zhang <guopeng.zhang@xxxxxxxxx>
> Link: https://lore.kernel.org/lkml/20261027123837.100909-1-guopeng.zhang@xxxxxxxxx
> Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
> ---
>  kernel/cgroup/cpuset.c                            | 12 ++++++++++++
>  tools/testing/selftests/cgroup/test_cpuset_prs.sh | 15 +++++++++++++++
>  2 files changed, 27 insertions(+)
> 
> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
> index 3219f927c35e..39c81a0a8ab9 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -2097,6 +2097,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
>  							     parent->effective_xcpus);
>  			if (!cpumask_empty(tmp->addmask))
>  				isolated_cpus_release(cs, tmp->addmask);
> +			/* Expansion of parent's effective_xcpus is handled below */
>  		}
>  		if (nocpu) {
>  			part_error = PERR_NOCPUS;
> @@ -2106,11 +2107,22 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
>  						     parent->effective_xcpus);
>  		} else if ((parent_prs == PRS_ISOLATED) &&
>  			   ((old_prs == PRS_ROOT) || (old_prs == -PRS_ROOT))) {
> +			/* Parent partition state changed to PRS_ISOLATED */
>  			part_error = PERR_ISOPARENT;
>  			if (old_prs == PRS_ROOT) {
>  				cpumask_copy(tmp->addmask, cs->effective_xcpus);
>  				adding = true;
>  			}
> +		} else if (is_partition_valid(cs) &&
> +			   !cpumask_equal(tmp->delmask, cs->effective_xcpus)) {
> +			/*
> +			 * If there is an expansion of parent's effective_xcpus,
> +			 * we may take more xcpus from parent. The parent's
> +			 * effective_cpus should still have active CPUs or nocpu
> +			 * should have been set.
> +			 */
> +			deleting = cpumask_andnot(tmp->delmask, tmp->delmask,
> +						  cs->effective_xcpus);
>  		} else if (is_partition_invalid(cs)) {
>  			struct cgroup_subsys_state *css;
>  			struct cpuset *child;
> diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
> index 83ef6c781af3..844efdf029cd 100755
> --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
> +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
> @@ -531,6 +531,21 @@ TEST_MATRIX=(
>  	" C1-4:P1 C3-4:P2   .      .    T:C4-6   .      .      .     0 A1:5-6|A2:4 A1:P1|A2:P2 4"
>  	" C1-4:P1 C1-2:P2   .      .    T:C4-6   .      .      .     0 A1:4-6|A2:4-6 A1:P1|A2:P-2 ."
>  
> +	# The extra CPUs gained by a child partition when its parent expands the
> +	# exclusive CPUs have to be taken away from the parent.
> +	" C2-6:X2-5:P1 CX3-6:P1 \
> +	                    .      .    X2-6     .      .      .     0 A1:2|A2:3-6|XA2:3-6 A1:P1|A2:P1 ."
> +	" C2-6:X2-5:P1 CX3-6:P2 \
> +	                    .      .    X2-6     .      .      .     0 A1:2|A2:3-6|XA2:3-6 A1:P1|A2:P2 3-6"
> +
> +	# Both expansion and contraction of parent's effective_xcpus will be
> +	# correctly handled in child partition and the child can be invalidated
> +	# if a populated parent could lose all its effective_cpus.
> +	" C2-6:X2-5:P1 CX3,5-6:P2 \
> +	                    .      .    X4-6     .      .      .     0 A1:4|A2:5-6|XA2:5-6 A1:P1|A2:P2 5-6"
> +	" C2-6:X2-5:P1 CX3-6:P2 \
> +	                    .      .   T:X4-6    .      .      .     0 A1:4-6|A2:4-6 A1:P1|A2:P-2 ."
> +
>  	#
>  	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
>  	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------

Reviewed-by: Guopeng Zhang <zhangguopeng@xxxxxxxxxx>
Tested-by: Guopeng Zhang <zhangguopeng@xxxxxxxxxx>

Thanks,
Guopeng