| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20190403084650.4414-4-juri.lelli@redhat.com>
Date: Wed, 3 Apr 2019 10:46:46 +0200
From: Juri Lelli <juri.lelli@...hat.com>
To: peterz@...radead.org, mingo@...hat.com, rostedt@...dmis.org,
tj@...nel.org
Cc: linux-kernel@...r.kernel.org, luca.abeni@...tannapisa.it,
claudio@...dence.eu.com, tommaso.cucinotta@...tannapisa.it,
bristot@...hat.com, mathieu.poirier@...aro.org, lizefan@...wei.com,
cgroups@...r.kernel.org, Juri Lelli <juri.lelli@...hat.com>
Subject: [PATCH v7 3/7] cgroup/cpuset: make callback_lock raw
callback_lock grants the holder read-only access to cpusets. For fixing
a synchronization issue between cpusets and scheduler core, it is now
required to make callback_lock available to core scheduler code.
Convert callback_lock to raw_spin_lock, so that it will be always safe
to acquire it from atomic context.
Unfortunately, callback_lock guards some user-controlled operations
(e.g., cpuset_cpus_allowed, cpuset_mems_allowed, etc.), which is usually
bad for a raw_spin_lock. Ideally we'd like to somehow avoid this, but we
have this behavior spread all over the place. A price we decide to pay
for the time being.
Signed-off-by: Juri Lelli <juri.lelli@...hat.com>
---
v6->v7: Added comment in changelog about callback_lock potential
problems w.r.t. userspace ops. [peterz]
---
kernel/cgroup/cpuset.c | 70 +++++++++++++++++++++---------------------
1 file changed, 35 insertions(+), 35 deletions(-)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 4834c4214e9c..ff9bd5abe613 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -333,7 +333,7 @@ static struct cpuset top_cpuset = {
*/
static DEFINE_MUTEX(cpuset_mutex);
-static DEFINE_SPINLOCK(callback_lock);
+static DEFINE_RAW_SPINLOCK(callback_lock);
static struct workqueue_struct *cpuset_migrate_mm_wq;
@@ -1235,7 +1235,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
* Newly added CPUs will be removed from effective_cpus and
* newly deleted ones will be added back to effective_cpus.
*/
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
if (adding) {
cpumask_or(parent->subparts_cpus,
parent->subparts_cpus, tmp->addmask);
@@ -1254,7 +1254,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
}
parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus);
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
return cmd == partcmd_update;
}
@@ -1359,7 +1359,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
continue;
rcu_read_unlock();
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
cpumask_copy(cp->effective_cpus, tmp->new_cpus);
if (cp->nr_subparts_cpus &&
@@ -1390,7 +1390,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
= cpumask_weight(cp->subparts_cpus);
}
}
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
WARN_ON(!is_in_v2_mode() &&
!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
@@ -1508,7 +1508,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
return -EINVAL;
}
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
/*
@@ -1519,7 +1519,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
cs->cpus_allowed);
cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
}
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
update_cpumasks_hier(cs, &tmp);
@@ -1713,9 +1713,9 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
continue;
rcu_read_unlock();
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
cp->effective_mems = *new_mems;
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
WARN_ON(!is_in_v2_mode() &&
!nodes_equal(cp->mems_allowed, cp->effective_mems));
@@ -1783,9 +1783,9 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
if (retval < 0)
goto done;
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
cs->mems_allowed = trialcs->mems_allowed;
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
/* use trialcs->mems_allowed as a temp variable */
update_nodemasks_hier(cs, &trialcs->mems_allowed);
@@ -1876,9 +1876,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs))
|| (is_spread_page(cs) != is_spread_page(trialcs)));
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
cs->flags = trialcs->flags;
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
rebuild_sched_domains_locked();
@@ -2381,7 +2381,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
cpuset_filetype_t type = seq_cft(sf)->private;
int ret = 0;
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
switch (type) {
case FILE_CPULIST:
@@ -2403,7 +2403,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
ret = -EINVAL;
}
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
return ret;
}
@@ -2713,14 +2713,14 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
cpuset_inc();
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
if (is_in_v2_mode()) {
cpumask_copy(cs->effective_cpus, parent->effective_cpus);
cs->effective_mems = parent->effective_mems;
cs->use_parent_ecpus = true;
parent->child_ecpus_count++;
}
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
goto out_unlock;
@@ -2747,12 +2747,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
}
rcu_read_unlock();
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
cs->mems_allowed = parent->mems_allowed;
cs->effective_mems = parent->mems_allowed;
cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
out_unlock:
mutex_unlock(&cpuset_mutex);
return 0;
@@ -2805,7 +2805,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
static void cpuset_bind(struct cgroup_subsys_state *root_css)
{
mutex_lock(&cpuset_mutex);
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
if (is_in_v2_mode()) {
cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
@@ -2816,7 +2816,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
top_cpuset.mems_allowed = top_cpuset.effective_mems;
}
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
mutex_unlock(&cpuset_mutex);
}
@@ -2917,12 +2917,12 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
{
bool is_empty;
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
cpumask_copy(cs->cpus_allowed, new_cpus);
cpumask_copy(cs->effective_cpus, new_cpus);
cs->mems_allowed = *new_mems;
cs->effective_mems = *new_mems;
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
/*
* Don't call update_tasks_cpumask() if the cpuset becomes empty,
@@ -2959,10 +2959,10 @@ hotplug_update_tasks(struct cpuset *cs,
if (nodes_empty(*new_mems))
*new_mems = parent_cs(cs)->effective_mems;
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
cpumask_copy(cs->effective_cpus, new_cpus);
cs->effective_mems = *new_mems;
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
if (cpus_updated)
update_tasks_cpumask(cs);
@@ -3117,7 +3117,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
/* synchronize cpus_allowed to cpu_active_mask */
if (cpus_updated) {
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
if (!on_dfl)
cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
/*
@@ -3137,17 +3137,17 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
}
}
cpumask_copy(top_cpuset.effective_cpus, &new_cpus);
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
/* we don't mess with cpumasks of tasks in top_cpuset */
}
/* synchronize mems_allowed to N_MEMORY */
if (mems_updated) {
- spin_lock_irq(&callback_lock);
+ raw_spin_lock_irq(&callback_lock);
if (!on_dfl)
top_cpuset.mems_allowed = new_mems;
top_cpuset.effective_mems = new_mems;
- spin_unlock_irq(&callback_lock);
+ raw_spin_unlock_irq(&callback_lock);
update_tasks_nodemask(&top_cpuset);
}
@@ -3248,11 +3248,11 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
{
unsigned long flags;
- spin_lock_irqsave(&callback_lock, flags);
+ raw_spin_lock_irqsave(&callback_lock, flags);
rcu_read_lock();
guarantee_online_cpus(task_cs(tsk), pmask);
rcu_read_unlock();
- spin_unlock_irqrestore(&callback_lock, flags);
+ raw_spin_unlock_irqrestore(&callback_lock, flags);
}
void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
@@ -3300,11 +3300,11 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
nodemask_t mask;
unsigned long flags;
- spin_lock_irqsave(&callback_lock, flags);
+ raw_spin_lock_irqsave(&callback_lock, flags);
rcu_read_lock();
guarantee_online_mems(task_cs(tsk), &mask);
rcu_read_unlock();
- spin_unlock_irqrestore(&callback_lock, flags);
+ raw_spin_unlock_irqrestore(&callback_lock, flags);
return mask;
}
@@ -3396,14 +3396,14 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask)
return true;
/* Not hardwall and node outside mems_allowed: scan up cpusets */
- spin_lock_irqsave(&callback_lock, flags);
+ raw_spin_lock_irqsave(&callback_lock, flags);
rcu_read_lock();
cs = nearest_hardwall_ancestor(task_cs(current));
allowed = node_isset(node, cs->mems_allowed);
rcu_read_unlock();
- spin_unlock_irqrestore(&callback_lock, flags);
+ raw_spin_unlock_irqrestore(&callback_lock, flags);
return allowed;
}
--
2.17.2
Powered by blists - more mailing lists