kernel/cgroup/cpuset.c

100 	 * cpuset.cpus and cpuset.mems, and won't be limited by the
443  * Cgroup v2 behavior is used on the "cpus" and "mems" control files when
446  * With v2 behavior, "cpus" and "mems" are always what the users have
448  * cpus or mems will be affected.
537  * online mems.  The top cpuset always has some mems online.
2122 		 * parent, which is guaranteed to have some MEMs.  in update_nodemasks_hier()
2153  * Handle user request to change the 'mems' memory placement
2685 	 * in effective cpus and mems. In that case, we can optimize out  in cpuset_attach()
2844  * Common handling for a write to a "cpus" or "mems" file.
2861 	 * As writes to "cpus" or "mems" may restore @cs's execution  in cpuset_write_resmask()
3077 		.name = "mems",
3184 		.name = "mems",
3199 		.name = "mems.effective",
3315 	 * (and likewise for mems) to the new cgroup.  in cpuset_css_online()
3795 	/* fetch the available cpus/mems and find out which changed how */  in cpuset_hotplug_workfn()
3852 	/* if cpus or mems changed, we need to propagate to descendants */  in cpuset_hotplug_workfn()
4112  *	GFP_USER     - only nodes in current tasks mems allowed ok.