On 05 Jan 2023 09:52:21 -0300 Marcelo Tosatti <mtosatti@xxxxxxxxxx>
> For nohz full CPUs, we'd like the per-CPU vm statistics to be
> synchronized when userspace is executing. Otherwise,
> the vmstat_shepherd might queue a work item to synchronize them,
> which is undesired intereference for isolated CPUs.
>
> This means that its necessary to check for, and possibly sync,
> the statistics when returning to userspace. This means that
> there are now two execution contexes, on different CPUs,
> which require awareness about each other: context switch
> and vmstat shepherd kernel threadr.
>
> To avoid the shared variables between these two contexes (which
> would require atomic accesses), delegate the responsability
> of statistics synchronization from vmstat_shepherd to local CPU
> context, for nohz_full CPUs.
>
> Do that by queueing a delayed work when marking per-CPU vmstat dirty.
>
> When returning to userspace, fold the stats and cancel the delayed work.
>
> When entering idle, only fold the stats.
>
> Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>
> ---
> include/linux/vmstat.h | 4 ++--
> kernel/time/tick-sched.c | 2 +-
> mm/vmstat.c | 41 ++++++++++++++++++++++++++++++++---------
> 3 files changed, 35 insertions(+), 12 deletions(-)
>
> Index: linux-2.6/mm/vmstat.c
> ===================================================================
> --- linux-2.6.orig/mm/vmstat.c
> +++ linux-2.6/mm/vmstat.c
> @@ -28,6 +28,7 @@
> #include <linux/mm_inline.h>
> #include <linux/page_ext.h>
> #include <linux/page_owner.h>
> +#include <linux/tick.h>
>
> #include "internal.h"
>
> @@ -194,21 +195,57 @@ void fold_vm_numa_events(void)
> #endif
>
> #ifdef CONFIG_SMP
> -static DEFINE_PER_CPU_ALIGNED(bool, vmstat_dirty);
> +
> +struct vmstat_dirty {
> + bool dirty;
> +#ifdef CONFIG_FLUSH_WORK_ON_RESUME_USER
> + bool cpu_offline;
> +#endif
> +};
> +
> +static DEFINE_PER_CPU_ALIGNED(struct vmstat_dirty, vmstat_dirty_pcpu);
> +static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
> +int sysctl_stat_interval __read_mostly = HZ;
> +
> +#ifdef CONFIG_FLUSH_WORK_ON_RESUME_USER
> +static inline void vmstat_queue_local_work(void)
> +{
> + bool vmstat_dirty = this_cpu_read(vmstat_dirty_pcpu.dirty);
> + bool cpu_offline = this_cpu_read(vmstat_dirty_pcpu.cpu_offline);
> + int cpu = smp_processor_id();
> +
> + if (tick_nohz_full_cpu(cpu) && !vmstat_dirty) {
> + struct delayed_work *dw;
> +
> + dw = this_cpu_ptr(&vmstat_work);
> + if (!delayed_work_pending(dw) && !cpu_offline) {
> + unsigned long delay;
> +
> + delay = round_jiffies_relative(sysctl_stat_interval);
> + queue_delayed_work_on(cpu, mm_percpu_wq, dw, delay);
Regression wrt V12 if timer is added on the CPU that is not doing HK_TYPE_TIMER?
> + }
> + }
> +}
> +#else
