From: Frederic Weisbecker <frederic@kernel.org>
To: Marcelo Tosatti <mtosatti@redhat.com>
Cc: linux-kernel@vger.kernel.org, Nitesh Lal <nilal@redhat.com>,
Nicolas Saenz Julienne <nsaenzju@redhat.com>,
Christoph Lameter <cl@linux.com>,
Juri Lelli <juri.lelli@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Alex Belits <abelits@belits.com>, Peter Xu <peterx@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Daniel Bristot de Oliveira <bristot@redhat.com>,
Oscar Shiang <oscar0225@livemail.tw>
Subject: Re: [patch v12 07/13] task isolation: sync vmstats conditional on changes
Date: Thu, 17 Mar 2022 15:51:43 +0100 [thread overview]
Message-ID: <20220317145143.GA459366@lothringen> (raw)
In-Reply-To: <20220315153314.042469218@fedora.localdomain>
On Tue, Mar 15, 2022 at 12:31:39PM -0300, Marcelo Tosatti wrote:
> Rather than syncing VM-stats on every return to userspace
> (or VM-entry), keep track of changes through a per-CPU bool.
>
> This improves performance when enabling task isolated
> for vcpu VMs.
>
> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
>
> ---
> v11:
> - Add TIF_TASK_ISOL bit to thread info flags and use it
> to decide whether to perform task isolation work on
> return to userspace
>
> include/linux/vmstat.h | 13 ++++++++++++-
> mm/vmstat.c | 29 ++++++++++++++++++++++++++++-
> 2 files changed, 40 insertions(+), 2 deletions(-)
>
> Index: linux-2.6/include/linux/vmstat.h
> ===================================================================
> --- linux-2.6.orig/include/linux/vmstat.h
> +++ linux-2.6/include/linux/vmstat.h
> @@ -22,7 +22,18 @@ int sysctl_vm_numa_stat_handler(struct c
> #endif
>
> #if defined(CONFIG_SMP) && defined(CONFIG_TASK_ISOLATION)
> -void sync_vmstat(void);
> +DECLARE_PER_CPU_ALIGNED(bool, vmstat_dirty);
> +
> +extern struct static_key vmstat_sync_enabled;
> +
> +void __sync_vmstat(void);
> +static inline void sync_vmstat(void)
> +{
> + if (static_key_false(&vmstat_sync_enabled))
> + __sync_vmstat();
> +}
> +
> +void init_sync_vmstat(void);
> #else
> static inline void sync_vmstat(void)
> {
> Index: linux-2.6/mm/vmstat.c
> ===================================================================
> --- linux-2.6.orig/mm/vmstat.c
> +++ linux-2.6/mm/vmstat.c
> @@ -334,6 +334,31 @@ void set_pgdat_percpu_threshold(pg_data_
> }
> }
>
> +#ifdef CONFIG_TASK_ISOLATION
> +struct static_key vmstat_sync_enabled;
> +DEFINE_PER_CPU_ALIGNED(bool, vmstat_dirty);
> +
> +static inline void mark_vmstat_dirty(void)
> +{
> + if (!static_key_false(&vmstat_sync_enabled))
> + return;
> +
> + raw_cpu_write(vmstat_dirty, true);
> + set_thread_flag(TIF_TASK_ISOL);
> +}
> +
> +void init_sync_vmstat(void)
> +{
> + raw_cpu_write(vmstat_dirty, true);
> + set_thread_flag(TIF_TASK_ISOL);
> +}
> +EXPORT_SYMBOL_GPL(vmstat_dirty);
> +#else
> +static inline void mark_vmstat_dirty(void)
> +{
> +}
> +#endif
> +
> /*
> * For use when we know that interrupts are disabled,
> * or when we know that preemption is disabled and that
> @@ -366,6 +391,7 @@ void __mod_zone_page_state(struct zone *
> x = 0;
> }
> __this_cpu_write(*p, x);
> + mark_vmstat_dirty();
>
> if (IS_ENABLED(CONFIG_PREEMPT_RT))
> preempt_enable();
> @@ -404,6 +430,7 @@ void __mod_node_page_state(struct pglist
> x = 0;
> }
> __this_cpu_write(*p, x);
> + mark_vmstat_dirty();
>
> if (IS_ENABLED(CONFIG_PREEMPT_RT))
> preempt_enable();
> @@ -602,6 +629,7 @@ static inline void mod_zone_state(struct
>
> if (z)
> zone_page_state_add(z, zone, item);
> + mark_vmstat_dirty();
> }
>
> void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
> @@ -670,6 +698,7 @@ static inline void mod_node_state(struct
>
> if (z)
> node_page_state_add(z, pgdat, item);
> + mark_vmstat_dirty();
> }
>
> void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
> @@ -1087,6 +1116,7 @@ static void fill_contig_page_info(struct
> info->free_blocks_suitable += blocks <<
> (order - suitable_order);
> }
> + mark_vmstat_dirty();
> }
>
> /*
> @@ -1443,6 +1473,7 @@ static void walk_zones_in_node(struct se
> if (!nolock)
> spin_unlock_irqrestore(&zone->lock, flags);
> }
> + mark_vmstat_dirty();
> }
> #endif
>
> @@ -1512,6 +1543,7 @@ static void pagetypeinfo_showfree_print(
> }
> seq_putc(m, '\n');
> }
> + mark_vmstat_dirty();
> }
>
> /* Print out the free pages at each order for each migatetype */
> @@ -1932,6 +1964,7 @@ static void vmstat_update(struct work_st
> this_cpu_ptr(&vmstat_work),
> round_jiffies_relative(sysctl_stat_interval));
> }
> + mark_vmstat_dirty();
> }
>
> /*
> @@ -2019,13 +2052,14 @@ static void vmstat_shepherd(struct work_
> }
>
> #ifdef CONFIG_TASK_ISOLATION
> -void sync_vmstat(void)
> +void __sync_vmstat(void)
> {
> int cpu;
>
> cpu = get_cpu();
>
> refresh_cpu_vm_stats(false);
> + raw_cpu_write(vmstat_dirty, false);
I still see a few raw_cpu_write() here, especially that one should
clearly become __this_cpu_write().
> put_cpu();
>
> /*
>
>
next prev parent reply other threads:[~2022-03-17 14:52 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-15 15:31 [patch v12 00/13] extensible prctl task isolation interface and vmstat sync Marcelo Tosatti
2022-03-15 15:31 ` [patch v12 01/13] s390: add support for TIF_TASK_ISOL Marcelo Tosatti
2022-03-15 15:31 ` [patch v12 02/13] x86: " Marcelo Tosatti
2022-03-15 15:31 ` [patch v12 03/13] add basic task isolation prctl interface Marcelo Tosatti
2022-04-25 22:23 ` Thomas Gleixner
2022-03-15 15:31 ` [patch v12 04/13] add prctl task isolation prctl docs and samples Marcelo Tosatti
2022-04-26 0:15 ` Thomas Gleixner
2022-03-15 15:31 ` [patch v12 05/13] task isolation: sync vmstats on return to userspace Marcelo Tosatti
2022-04-25 23:06 ` Thomas Gleixner
2022-04-27 6:56 ` Thomas Gleixner
2022-03-15 15:31 ` [patch v12 06/13] procfs: add per-pid task isolation state Marcelo Tosatti
2022-04-25 23:27 ` Thomas Gleixner
2022-03-15 15:31 ` [patch v12 07/13] task isolation: sync vmstats conditional on changes Marcelo Tosatti
2022-03-17 14:51 ` Frederic Weisbecker [this message]
2022-04-27 8:03 ` Thomas Gleixner
2022-03-15 15:31 ` [patch v12 08/13] task isolation: enable return to userspace processing Marcelo Tosatti
2022-03-15 15:31 ` [patch v12 09/13] task isolation: add preempt notifier to sync per-CPU vmstat dirty info to thread info Marcelo Tosatti
2022-03-16 2:41 ` Oscar Shiang
2022-04-27 7:11 ` Thomas Gleixner
2022-04-27 12:09 ` Thomas Gleixner
2022-05-04 16:32 ` Marcelo Tosatti
2022-05-04 17:39 ` Thomas Gleixner
2022-03-15 15:31 ` [patch v12 10/13] KVM: x86: process isolation work from VM-entry code path Marcelo Tosatti
2022-03-15 15:31 ` [patch v12 11/13] mm: vmstat: move need_update Marcelo Tosatti
2022-03-15 15:31 ` [patch v12 12/13] mm: vmstat_refresh: avoid queueing work item if cpu stats are clean Marcelo Tosatti
2022-04-27 7:23 ` Thomas Gleixner
2022-05-03 19:17 ` Marcelo Tosatti
2022-03-15 15:31 ` [patch v12 13/13] task isolation: only TIF_TASK_ISOL if task isolation is enabled Marcelo Tosatti
2022-04-27 7:45 ` Thomas Gleixner
2022-05-03 19:12 ` Marcelo Tosatti
2022-05-04 13:03 ` Thomas Gleixner
2022-03-17 15:08 ` [patch v12 00/13] extensible prctl task isolation interface and vmstat sync Frederic Weisbecker
2022-04-25 16:29 ` Marcelo Tosatti
2022-04-25 21:12 ` Thomas Gleixner
2022-05-03 18:57 ` Marcelo Tosatti
2022-04-27 9:19 ` Christoph Lameter
2022-05-03 18:57 ` Marcelo Tosatti
2022-05-04 13:20 ` Thomas Gleixner
2022-05-04 18:56 ` Marcelo Tosatti
2022-05-04 20:15 ` Thomas Gleixner
2022-05-05 16:52 ` Marcelo Tosatti
2022-06-01 16:14 ` Marcelo Tosatti
2022-05-04 17:01 ` Tim Chen
2022-05-04 20:08 ` Marcelo Tosatti
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220317145143.GA459366@lothringen \
--to=frederic@kernel.org \
--cc=abelits@belits.com \
--cc=bristot@redhat.com \
--cc=cl@linux.com \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=nilal@redhat.com \
--cc=nsaenzju@redhat.com \
--cc=oscar0225@livemail.tw \
--cc=peterx@redhat.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox