cgroup/cpuset: Change cpuset_rwsem and hotplug lock order

stable inclusion
from stable-v4.19.280
commit 224262583fabf3b6bf2a29d033cf9a8f28fde843
category: bugfix
bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6TI3Y
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=224262583fabf3b6bf2a29d033cf9a8f28fde843

--------------------------------

commit d74b27d6 upstream.

commit 1243dc51 ("cgroup/cpuset: Convert cpuset_mutex to
percpu_rwsem") is performance patch which is not backport. So
convert percpu_rwsem to cpuset_mutex.

commit aa44002e7db25 ("cpuset: Fix unsafe lock order between
cpuset lock and cpuslock") makes lock order keep cpuset_mutex
->cpu_hotplug_lock. We should change lock order in cpuset_attach.

original commit message:

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).
Tested-by: NDietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: NJuri Lelli <juri.lelli@redhat.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bristot@redhat.com
Cc: claudio@evidence.eu.com
Cc: lizefan@huawei.com
Cc: longman@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: mathieu.poirier@linaro.org
Cc: rostedt@goodmis.org
Cc: tj@kernel.org
Cc: tommaso.cucinotta@santannapisa.it
Link: https://lkml.kernel.org/r/20190719140000.31694-7-juri.lelli@redhat.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
Signed-off-by: NCai Xinchen <caixinchen1@huawei.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NCai Xinchen <caixinchen1@huawei.com>
Reviewed-by: NWang Weiyang <wangweiyang2@huawei.com>
Signed-off-by: NYongqiang Liu <liuyongqiang13@huawei.com>

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);

kernel/cgroup/cpuset.c

@@ -914,8 +914,8 @@ static void rebuild_sched_domains_locked(void)
 	cpumask_var_t *doms;
 	int ndoms;
 
+	lockdep_assert_cpus_held();
 	lockdep_assert_held(&cpuset_mutex);
-	get_online_cpus();
 
 	/*
 	 * We have raced with CPU hotplug. Don't do anything to avoid
@@ -923,15 +923,13 @@ static void rebuild_sched_domains_locked(void)
 	 * Anyways, hotplug work item will rebuild sched domains.
 	 */
 	if (!cpumask_equal(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_sched_domains(ndoms, doms, attr);
-out:
-	put_online_cpus();
 }
 #else /* !CONFIG_SMP */
 static void rebuild_sched_domains_locked(void)
@@ -941,9 +939,11 @@ static void rebuild_sched_domains_locked(void)
 
 void rebuild_sched_domains(void)
 {
+	get_online_cpus();
 	mutex_lock(&cpuset_mutex);
 	rebuild_sched_domains_locked();
 	mutex_unlock(&cpuset_mutex);
+	put_online_cpus();
 }
 
 /**
@@ -1612,13 +1612,13 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 	cgroup_taskset_first(tset, &css);
 	cs = css_cs(css);
 
-	mutex_lock(&cpuset_mutex);
-
 	/*
 	 * It should hold cpus lock because a cpu offline event can
 	 * cause set_cpus_allowed_ptr() failed.
 	 */
 	get_online_cpus();
+	mutex_lock(&cpuset_mutex);
+
 	/* prepare for attach */
 	if (cs == &top_cpuset)
 		cpumask_copy(cpus_attach, cpu_possible_mask);
@@ -1644,7 +1644,6 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 		cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to);
 		cpuset_update_task_spread_flag(cs, task);
 	}
-       put_online_cpus();
 
 	/*
 	 * Change mm for all threadgroup leaders. This is expensive and may
@@ -1680,6 +1679,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 		wake_up(&cpuset_attach_wq);
 
 	mutex_unlock(&cpuset_mutex);
+	put_online_cpus();
 }
 
 /* The various types of files and directories in a cpuset file system */
@@ -1711,6 +1711,7 @@ 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();
 	mutex_lock(&cpuset_mutex);
 	if (!is_cpuset_online(cs)) {
 		retval = -ENODEV;
@@ -1748,6 +1749,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
 	}
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
+	put_online_cpus();
 	return retval;
 }
 
@@ -1758,6 +1760,7 @@ 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();
 	mutex_lock(&cpuset_mutex);
 	if (!is_cpuset_online(cs))
 		goto out_unlock;
@@ -1772,6 +1775,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
 	}
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
+	put_online_cpus();
 	return retval;
 }
 
@@ -1810,6 +1814,7 @@ 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();
 	mutex_lock(&cpuset_mutex);
 	if (!is_cpuset_online(cs))
 		goto out_unlock;
@@ -1840,6 +1845,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	free_trial_cpuset(trialcs);
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
+	put_online_cpus();
 	kernfs_unbreak_active_protection(of->kn);
 	css_put(&cs->css);
 	flush_workqueue(cpuset_migrate_mm_wq);
@@ -2108,6 +2114,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	if (!parent)
 		return 0;
 
+	get_online_cpus();
 	mutex_lock(&cpuset_mutex);
 
 	set_bit(CS_ONLINE, &cs->flags);
@@ -2161,6 +2168,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	spin_unlock_irq(&callback_lock);
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
+	put_online_cpus();
 	return 0;
 }
 
@@ -2174,6 +2182,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 {
 	struct cpuset *cs = css_cs(css);
 
+	get_online_cpus();
 	mutex_lock(&cpuset_mutex);
 
 	if (is_sched_load_balance(cs))
@@ -2183,6 +2192,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 	clear_bit(CS_ONLINE, &cs->flags);
 
 	mutex_unlock(&cpuset_mutex);
+	put_online_cpus();
 }
 
 static void cpuset_css_free(struct cgroup_subsys_state *css)