From: Juri Lelli <juri.lelli@redhat.com>
To: peterz@infradead.org, mingo@redhat.com, rostedt@goodmis.org,
tj@kernel.org
Cc: linux-kernel@vger.kernel.org, luca.abeni@santannapisa.it,
claudio@evidence.eu.com, tommaso.cucinotta@santannapisa.it,
bristot@redhat.com, mathieu.poirier@linaro.org,
lizefan@huawei.com, longman@redhat.com, dietmar.eggemann@arm.com,
cgroups@vger.kernel.org, Juri Lelli <juri.lelli@redhat.com>
Subject: [PATCH v9 6/8] cgroup/cpuset: Change cpuset_rwsem and hotplug lock order
Date: Fri, 19 Jul 2019 15:59:58 +0200 [thread overview]
Message-ID: <20190719140000.31694-7-juri.lelli@redhat.com> (raw)
In-Reply-To: <20190719140000.31694-1-juri.lelli@redhat.com>
cpuset_rwsem is going to be acquired from sched_setscheduler() with a
following patch. There are however paths (e.g., spawn_ksoftirqd) in
which sched_scheduler() is eventually called while holding hotplug lock;
this creates a dependecy between hotplug lock (to be always acquired
first) and cpuset_rwsem (to be always acquired after hotplug lock).
Fix paths which currently take the two locks in the wrong order (after
a following patch is applied).
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
---
include/linux/cpuset.h | 8 ++++----
kernel/cgroup/cpuset.c | 22 +++++++++++++++++-----
2 files changed, 21 insertions(+), 9 deletions(-)
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 934633a05d20..7f1478c26a33 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -40,14 +40,14 @@ static inline bool cpusets_enabled(void)
static inline void cpuset_inc(void)
{
- static_branch_inc(&cpusets_pre_enable_key);
- static_branch_inc(&cpusets_enabled_key);
+ static_branch_inc_cpuslocked(&cpusets_pre_enable_key);
+ static_branch_inc_cpuslocked(&cpusets_enabled_key);
}
static inline void cpuset_dec(void)
{
- static_branch_dec(&cpusets_enabled_key);
- static_branch_dec(&cpusets_pre_enable_key);
+ static_branch_dec_cpuslocked(&cpusets_enabled_key);
+ static_branch_dec_cpuslocked(&cpusets_pre_enable_key);
}
extern int cpuset_init(void);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 85491d09f3d3..93414ea63252 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1026,8 +1026,8 @@ static void rebuild_sched_domains_locked(void)
cpumask_var_t *doms;
int ndoms;
+ lockdep_assert_cpus_held();
percpu_rwsem_assert_held(&cpuset_rwsem);
- get_online_cpus();
/*
* We have raced with CPU hotplug. Don't do anything to avoid
@@ -1036,19 +1036,17 @@ static void rebuild_sched_domains_locked(void)
*/
if (!top_cpuset.nr_subparts_cpus &&
!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
- goto out;
+ return;
if (top_cpuset.nr_subparts_cpus &&
!cpumask_subset(top_cpuset.effective_cpus, cpu_active_mask))
- goto out;
+ return;
/* Generate domain masks and attrs */
ndoms = generate_sched_domains(&doms, &attr);
/* Have scheduler rebuild the domains */
partition_and_rebuild_sched_domains(ndoms, doms, attr);
-out:
- put_online_cpus();
}
#else /* !CONFIG_SMP */
static void rebuild_sched_domains_locked(void)
@@ -1058,9 +1056,11 @@ static void rebuild_sched_domains_locked(void)
void rebuild_sched_domains(void)
{
+ get_online_cpus();
percpu_down_write(&cpuset_rwsem);
rebuild_sched_domains_locked();
percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
}
/**
@@ -2298,6 +2298,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
cpuset_filetype_t type = cft->private;
int retval = 0;
+ get_online_cpus();
percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs)) {
retval = -ENODEV;
@@ -2335,6 +2336,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
}
out_unlock:
percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
return retval;
}
@@ -2345,6 +2347,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
cpuset_filetype_t type = cft->private;
int retval = -ENODEV;
+ get_online_cpus();
percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs))
goto out_unlock;
@@ -2359,6 +2362,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
}
out_unlock:
percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
return retval;
}
@@ -2397,6 +2401,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
kernfs_break_active_protection(of->kn);
flush_work(&cpuset_hotplug_work);
+ get_online_cpus();
percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs))
goto out_unlock;
@@ -2422,6 +2427,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
free_cpuset(trialcs);
out_unlock:
percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
kernfs_unbreak_active_protection(of->kn);
css_put(&cs->css);
flush_workqueue(cpuset_migrate_mm_wq);
@@ -2552,6 +2558,7 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
return -EINVAL;
css_get(&cs->css);
+ get_online_cpus();
percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs))
goto out_unlock;
@@ -2559,6 +2566,7 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
retval = update_prstate(cs, val);
out_unlock:
percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
css_put(&cs->css);
return retval ?: nbytes;
}
@@ -2764,6 +2772,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
if (!parent)
return 0;
+ get_online_cpus();
percpu_down_write(&cpuset_rwsem);
set_bit(CS_ONLINE, &cs->flags);
@@ -2816,6 +2825,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
spin_unlock_irq(&callback_lock);
out_unlock:
percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
return 0;
}
@@ -2834,6 +2844,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
{
struct cpuset *cs = css_cs(css);
+ get_online_cpus();
percpu_down_write(&cpuset_rwsem);
if (is_partition_root(cs))
@@ -2854,6 +2865,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
clear_bit(CS_ONLINE, &cs->flags);
percpu_up_write(&cpuset_rwsem);
+ put_online_cpus();
}
static void cpuset_css_free(struct cgroup_subsys_state *css)
--
2.17.2
next prev parent reply other threads:[~2019-07-19 14:00 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-19 13:59 [PATCH v9 0/8] sched/deadline: fix cpusets bandwidth accounting Juri Lelli
2019-07-19 13:59 ` [PATCH v9 1/8] sched/topology: Adding function partition_sched_domains_locked() Juri Lelli
2019-07-25 16:19 ` [tip:sched/core] sched/topology: Add partition_sched_domains_locked() tip-bot for Mathieu Poirier
2019-07-19 13:59 ` [PATCH v9 2/8] sched/core: Streamlining calls to task_rq_unlock() Juri Lelli
2019-07-22 8:21 ` Dietmar Eggemann
2019-07-22 8:32 ` Juri Lelli
2019-07-22 9:08 ` Dietmar Eggemann
2019-07-23 10:32 ` Peter Zijlstra
2019-07-23 10:31 ` Peter Zijlstra
2019-07-23 13:11 ` Tejun Heo
2019-07-23 14:58 ` Juri Lelli
2019-07-25 16:20 ` [tip:sched/core] sched/core: Streamle " tip-bot for Mathieu Poirier
2019-07-19 13:59 ` [PATCH v9 3/8] cpuset: Rebuild root domain deadline accounting information Juri Lelli
2019-07-25 13:53 ` Ingo Molnar
2019-07-25 13:56 ` Ingo Molnar
2019-07-25 14:07 ` Juri Lelli
2019-07-25 16:00 ` Mathieu Poirier
2019-07-25 16:21 ` [tip:sched/core] cpusets: " tip-bot for Mathieu Poirier
2019-11-04 18:57 ` [PATCH v9 3/8] cpuset: " Michal Koutný
2019-11-05 12:03 ` Michal Koutný
2022-12-16 23:35 ` Qais Yousef
2022-12-17 2:26 ` Waiman Long
2022-12-17 22:10 ` Qais Yousef
2022-12-19 8:07 ` Vincent Guittot
2022-12-20 11:43 ` Qais Yousef
2023-01-15 16:41 ` Qais Yousef
2019-07-19 13:59 ` [PATCH v9 4/8] sched/deadline: Fix bandwidth accounting at all levels after offline migration Juri Lelli
2019-07-22 11:07 ` Dietmar Eggemann
2019-07-22 12:28 ` Juri Lelli
2019-07-22 13:21 ` Dietmar Eggemann
2019-07-22 13:35 ` Juri Lelli
2019-07-22 14:29 ` Dietmar Eggemann
2019-07-25 16:21 ` [tip:sched/core] " tip-bot for Juri Lelli
2019-07-19 13:59 ` [PATCH v9 5/8] cgroup/cpuset: convert cpuset_mutex to percpu_rwsem Juri Lelli
2019-07-25 16:22 ` [tip:sched/core] cgroup/cpuset: Convert " tip-bot for Juri Lelli
2019-07-19 13:59 ` Juri Lelli [this message]
2019-07-25 16:23 ` [tip:sched/core] cgroup/cpuset: Change cpuset_rwsem and hotplug lock order tip-bot for Juri Lelli
2019-07-19 13:59 ` [PATCH v9 7/8] rcu/tree: Setschedule gp ktread to SCHED_FIFO outside of atomic region Juri Lelli
2019-07-25 16:24 ` [tip:sched/core] rcu/tree: Call setschedule() " tip-bot for Juri Lelli
2019-07-19 14:00 ` [PATCH v9 8/8] sched/core: Prevent race condition between cpuset and __sched_setscheduler() Juri Lelli
2019-07-25 16:24 ` [tip:sched/core] " tip-bot for Juri Lelli
2019-07-24 8:45 ` [PATCH v9 0/8] sched/deadline: fix cpusets bandwidth accounting Dietmar Eggemann
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=20190719140000.31694-7-juri.lelli@redhat.com \
--to=juri.lelli@redhat.com \
--cc=bristot@redhat.com \
--cc=cgroups@vger.kernel.org \
--cc=claudio@evidence.eu.com \
--cc=dietmar.eggemann@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lizefan@huawei.com \
--cc=longman@redhat.com \
--cc=luca.abeni@santannapisa.it \
--cc=mathieu.poirier@linaro.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tj@kernel.org \
--cc=tommaso.cucinotta@santannapisa.it \
/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;
as well as URLs for NNTP newsgroup(s).