summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorElena Reshetova <elena.reshetova@intel.com>2019-01-18 14:27:29 +0200
committerIngo Molnar <mingo@kernel.org>2019-02-04 08:53:55 +0100
commitec1d281923cf81cc660343d0cb8ffc837ffb991d (patch)
treebe2576e169663fe7c0f95338d819a90e8ef095fc
parentc45a77952427b678aa9205e1b0ee3bcf33339a2e (diff)
downloadlinux-ec1d281923cf81cc660343d0cb8ffc837ffb991d.tar.gz
linux-ec1d281923cf81cc660343d0cb8ffc837ffb991d.tar.bz2
linux-ec1d281923cf81cc660343d0cb8ffc837ffb991d.zip
sched/core: Convert task_struct.usage to refcount_t
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. ** Important note for maintainers: Some functions from refcount_t API defined in lib/refcount.c have different memory ordering guarantees than their atomic counterparts. The full comparison can be seen in https://lkml.org/lkml/2017/11/15/57 and it is hopefully soon in state to be merged to the documentation tree. Normally the differences should not matter since refcount_t provides enough guarantees to satisfy the refcounting use cases, but in some rare cases it might matter. Please double check that you don't have some undocumented memory guarantees for this variable usage. For the task_struct.usage it might make a difference in following places: - put_task_struct(): decrement in refcount_dec_and_test() only provides RELEASE ordering and control dependency on success vs. fully ordered atomic counterpart Suggested-by: Kees Cook <keescook@chromium.org> Signed-off-by: Elena Reshetova <elena.reshetova@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: David Windsor <dwindsor@gmail.com> Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com> Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: akpm@linux-foundation.org Cc: viro@zeniv.linux.org.uk Link: https://lkml.kernel.org/r/1547814450-18902-5-git-send-email-elena.reshetova@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
-rw-r--r--include/linux/sched.h3
-rw-r--r--include/linux/sched/task.h4
-rw-r--r--init/init_task.c2
-rw-r--r--kernel/fork.c4
4 files changed, 7 insertions, 6 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e2bba022827d..9d14d6864ca6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -21,6 +21,7 @@
#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>
@@ -607,7 +608,7 @@ 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 44c6f15800ff..2e97a2227045 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -88,13 +88,13 @@ 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/init/init_task.c b/init/init_task.c
index 9aa3ebc74970..aca34c89529f 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -65,7 +65,7 @@ struct task_struct init_task
#endif
.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/kernel/fork.c b/kernel/fork.c
index 935a42d5f8ff..3f7e192e29f2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -717,7 +717,7 @@ 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);
@@ -896,7 +896,7 @@ 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