atomic_t variables are currently used to implement reference
counters with the following properties:
- counter is initialized to 1 using atomic_set()
- a resource is freed upon counter reaching zero
- once counter reaches zero, its further
increments aren't allowed
- counter schema uses basic atomic operations
(set, inc, inc_not_zero, dec_and_test, etc.)
Such atomic variables should be converted to a newly provided
refcount_t type and API that prevents accidental counter overflows
and underflows. This is important since overflows and underflows
can lead to use-after-free situation and be exploitable.
The variable task_struct.usage is used as pure reference counter.
Convert it to refcount_t and fix up the operations.
Suggested-by: Kees Cook <keescook@xxxxxxxxxxxx>
Reviewed-by: David Windsor <dwindsor@xxxxxxxxx>
Reviewed-by: Hans Liljestrand <ishkamiel@xxxxxxxxx>
Signed-off-by: Elena Reshetova <elena.reshetova@xxxxxxxxx>
---
include/linux/init_task.h | 2 +-
include/linux/sched.h | 3 ++-
include/linux/sched/task.h | 4 ++--
kernel/fork.c | 4 ++--
4 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 6c6f520..d312376 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -227,7 +227,7 @@ extern struct cred init_cred;
INIT_TASK_TI(tsk) \
.state = 0, \
.stack = init_stack, \
- .usage = ATOMIC_INIT(2), \
+ .usage = REFCOUNT_INIT(2), \
.flags = PF_KTHREAD, \
.prio = MAX_PRIO-20, \
.static_prio = MAX_PRIO-20, \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6110471..1eeb300 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -20,6 +20,7 @@
#include <linux/seccomp.h>
#include <linux/nodemask.h>
#include <linux/rcupdate.h>
+#include <linux/refcount.h>
#include <linux/resource.h>
#include <linux/latencytop.h>
#include <linux/sched/prio.h>
@@ -534,7 +535,7 @@ struct task_struct {
randomized_struct_fields_start
void *stack;
- atomic_t usage;
+ refcount_t usage;
/* Per task flags (PF_*), defined further below: */
unsigned int flags;
unsigned int ptrace;
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 79a2a74..2ddc9b0 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -85,13 +85,13 @@ extern void sched_exec(void);
#define sched_exec() {}
#endif
-#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
+#define get_task_struct(tsk) do { refcount_inc(&(tsk)->usage); } while(0)
extern void __put_task_struct(struct task_struct *t);
static inline void put_task_struct(struct task_struct *t)
{
- if (atomic_dec_and_test(&t->usage))
+ if (refcount_dec_and_test(&t->usage))
__put_task_struct(t);
}
diff --git a/kernel/fork.c b/kernel/fork.c
index d2e2eb0..1e54683 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -407,7 +407,7 @@ static inline void put_signal_struct(struct signal_struct *sig)
void __put_task_struct(struct task_struct *tsk)
{
WARN_ON(!tsk->exit_state);
- WARN_ON(atomic_read(&tsk->usage));
+ WARN_ON(refcount_read(&tsk->usage));
WARN_ON(tsk == current);
cgroup_free(tsk);
@@ -564,7 +564,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
* One for us, one for whoever does the "release_task()" (usually
* parent)
*/
- atomic_set(&tsk->usage, 2);
+ refcount_set(&tsk->usage, 2);
#ifdef CONFIG_BLK_DEV_IO_TRACE
tsk->btrace_seq = 0;
#endif
--
2.7.4
