From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752725AbeCWXOG (ORCPT ); Fri, 23 Mar 2018 19:14:06 -0400 Received: from mail-yb0-f196.google.com ([209.85.213.196]:38744 "EHLO mail-yb0-f196.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752444AbeCWXNj (ORCPT ); Fri, 23 Mar 2018 19:13:39 -0400 X-Google-Smtp-Source: AG47ELsNBOInef5BEg289MURflssZ+Du6pN4xBeY7hu6aM7dadYwJAqT6uh2I+ncvbI2bTVc7IUrwA== From: Tejun Heo To: lizefan@huawei.com, hannes@cmpxchg.org Cc: cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, guro@fb.com, kernel-team@fb.com, Tejun Heo Subject: [PATCH 7/8] cgroup: Add cgroup_subsys->css_rstat_flush() Date: Fri, 23 Mar 2018 16:13:12 -0700 Message-Id: <20180323231313.1254142-8-tj@kernel.org> X-Mailer: git-send-email 2.9.5 In-Reply-To: <20180323231313.1254142-1-tj@kernel.org> References: <20180323231313.1254142-1-tj@kernel.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This patch adds cgroup_subsys->css_rstat_flush(). If a subsystem has this callback, its csses are linked on cgrp->css_rstat_list and rstat will call the function whenever the associated cgroup is flushed. Flush is also performed when such csses are released so that residual counts aren't lost. Combined with the rstat API previous patches factored out, this allows controllers to plug into rstat to manage their statistics in a scalable way. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 5 +++++ kernel/cgroup/cgroup.c | 11 +++++++++++ kernel/cgroup/rstat.c | 11 ++++++++++- 3 files changed, 26 insertions(+), 1 deletion(-) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index cf9db7b..8b8dd17 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -130,6 +130,9 @@ struct cgroup_subsys_state { struct list_head sibling; struct list_head children; + /* flush target list anchored at cgrp->rstat_css_list */ + struct list_head rstat_css_node; + /* * PI: Subsys-unique ID. 0 is unused and root is always 1. The * matching css can be looked up using css_from_id(). @@ -412,6 +415,7 @@ struct cgroup { /* per-cpu recursive resource statistics */ struct cgroup_rstat_cpu __percpu *rstat_cpu; + struct list_head rstat_css_list; /* cgroup basic resource statistics */ struct cgroup_base_stat pending_bstat; /* pending from children */ @@ -577,6 +581,7 @@ struct cgroup_subsys { void (*css_released)(struct cgroup_subsys_state *css); void (*css_free)(struct cgroup_subsys_state *css); void (*css_reset)(struct cgroup_subsys_state *css); + void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu); int (*css_extra_stat_show)(struct seq_file *seq, struct cgroup_subsys_state *css); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 0d3d093..f29f84e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1860,6 +1860,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) cgrp->dom_cgrp = cgrp; cgrp->max_descendants = INT_MAX; cgrp->max_depth = INT_MAX; + INIT_LIST_HEAD(&cgrp->rstat_css_list); prev_cputime_init(&cgrp->prev_cputime); for_each_subsys(ss, ssid) @@ -4630,6 +4631,11 @@ static void css_release_work_fn(struct work_struct *work) if (ss) { /* css release path */ + if (!list_empty(&css->rstat_css_node)) { + cgroup_rstat_flush(cgrp); + list_del_rcu(&css->rstat_css_node); + } + cgroup_idr_replace(&ss->css_idr, NULL, css->id); if (ss->css_released) ss->css_released(css); @@ -4690,6 +4696,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css, css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); + INIT_LIST_HEAD(&css->rstat_css_node); css->serial_nr = css_serial_nr_next++; atomic_set(&css->online_cnt, 0); @@ -4698,6 +4705,9 @@ static void init_and_link_css(struct cgroup_subsys_state *css, css_get(css->parent); } + if (cgroup_on_dfl(cgrp) && ss->css_rstat_flush) + list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list); + BUG_ON(cgroup_css(cgrp, ss)); } @@ -4799,6 +4809,7 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, err_list_del: list_del_rcu(&css->sibling); err_free_css: + list_del_rcu(&css->rstat_css_node); call_rcu(&css->rcu_head, css_free_rcu_fn); return ERR_PTR(err); } diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index a5f9338..18b464a 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -143,8 +143,17 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) struct cgroup *pos = NULL; raw_spin_lock(cpu_lock); - while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) + while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { + struct cgroup_subsys_state *css; + cgroup_base_stat_flush(pos, cpu); + + rcu_read_lock(); + list_for_each_entry_rcu(css, &pos->rstat_css_list, + rstat_css_node) + css->ss->css_rstat_flush(css, cpu); + rcu_read_unlock(); + } raw_spin_unlock(cpu_lock); /* if @may_sleep, play nice and yield if necessary */ -- 2.9.5