cgroup: fix RCU accesses to task->cgroups

commit 14611e51a57df10240817d8ada510842faf0ec51 upstream.

task->cgroups is a RCU pointer pointing to struct css_set.  A task
switches to a different css_set on cgroup migration but a css_set
doesn't change once created and its pointers to cgroup_subsys_states
aren't RCU protected.

task_subsys_state[_check]() is the macro to acquire css given a task
and subsys_id pair.  It RCU-dereferences task->cgroups->subsys[] not
task->cgroups, so the RCU pointer task->cgroups ends up being
dereferenced without read_barrier_depends() after it.  It's broken.

Fix it by introducing task_css_set[_check]() which does
RCU-dereference on task->cgroups.  task_subsys_state[_check]() is
reimplemented to directly dereference ->subsys[] of the css_set
returned from task_css_set[_check]().

This removes some of sparse RCU warnings in cgroup.

v2: Fixed unbalanced parenthsis and there's no need to use
    rcu_dereference_raw() when !CONFIG_PROVE_RCU.  Both spotted by Li.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 48 insertions, 10 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 8bda1294c035..8852d370c720 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -646,22 +646,60 @@ static inline struct cgroup_subsys_state *cgroup_subsys_state(
         return cgrp->subsys[subsys_id];
 }
 
-/*
- * function to get the cgroup_subsys_state which allows for extra
- * rcu_dereference_check() conditions, such as locks used during the
- * cgroup_subsys::attach() methods.
+/**
+ * task_css_set_check - obtain a task's css_set with extra access conditions
+ * @task: the task to obtain css_set for
+ * @__c: extra condition expression to be passed to rcu_dereference_check()
+ *
+ * A task's css_set is RCU protected, initialized and exited while holding
+ * task_lock(), and can only be modified while holding both cgroup_mutex
+ * and task_lock() while the task is alive.  This macro verifies that the
+ * caller is inside proper critical section and returns @task's css_set.
+ *
+ * The caller can also specify additional allowed conditions via @__c, such
+ * as locks used during the cgroup_subsys::attach() methods.
  */
 #ifdef CONFIG_PROVE_RCU
 extern struct mutex cgroup_mutex;
-#define task_subsys_state_check(task, subsys_id, __c)                   \
-        rcu_dereference_check((task)->cgroups->subsys[(subsys_id)],     \
-                              lockdep_is_held(&(task)->alloc_lock) ||   \
-                              lockdep_is_held(&cgroup_mutex) || (__c))
+#define task_css_set_check(task, __c)                                   \
+        rcu_dereference_check((task)->cgroups,                          \
+                lockdep_is_held(&(task)->alloc_lock) ||                 \
+                lockdep_is_held(&cgroup_mutex) || (__c))
 #else
-#define task_subsys_state_check(task, subsys_id, __c)                   \
-        rcu_dereference((task)->cgroups->subsys[(subsys_id)])
+#define task_css_set_check(task, __c)                                   \
+        rcu_dereference((task)->cgroups)
 #endif
 
+/**
+ * task_subsys_state_check - obtain css for (task, subsys) w/ extra access conds
+ * @task: the target task
+ * @subsys_id: the target subsystem ID
+ * @__c: extra condition expression to be passed to rcu_dereference_check()
+ *
+ * Return the cgroup_subsys_state for the (@task, @subsys_id) pair.  The
+ * synchronization rules are the same as task_css_set_check().
+ */
+#define task_subsys_state_check(task, subsys_id, __c)                   \
+        task_css_set_check((task), (__c))->subsys[(subsys_id)]
+
+/**
+ * task_css_set - obtain a task's css_set
+ * @task: the task to obtain css_set for
+ *
+ * See task_css_set_check().
+ */
+static inline struct css_set *task_css_set(struct task_struct *task)
+{
+        return task_css_set_check(task, false);
+}
+
+/**
+ * task_subsys_state - obtain css for (task, subsys)
+ * @task: the target task
+ * @subsys_id: the target subsystem ID
+ *
+ * See task_subsys_state_check().
+ */
 static inline struct cgroup_subsys_state *
 task_subsys_state(struct task_struct *task, int subsys_id)
 {