Commit ec1d2819 authored by Elena Reshetova's avatar Elena Reshetova Committed by Ingo Molnar

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: default avatarKees Cook <keescook@chromium.org>
Signed-off-by: default avatarElena Reshetova <elena.reshetova@intel.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: default avatarDavid Windsor <dwindsor@gmail.com>
Reviewed-by: default avatarHans Liljestrand <ishkamiel@gmail.com>
Reviewed-by: default avatarAndrea 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.comSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent c45a7795
...@@ -21,6 +21,7 @@ ...@@ -21,6 +21,7 @@
#include <linux/seccomp.h> #include <linux/seccomp.h>
#include <linux/nodemask.h> #include <linux/nodemask.h>
#include <linux/rcupdate.h> #include <linux/rcupdate.h>
#include <linux/refcount.h>
#include <linux/resource.h> #include <linux/resource.h>
#include <linux/latencytop.h> #include <linux/latencytop.h>
#include <linux/sched/prio.h> #include <linux/sched/prio.h>
...@@ -607,7 +608,7 @@ struct task_struct { ...@@ -607,7 +608,7 @@ struct task_struct {
randomized_struct_fields_start randomized_struct_fields_start
void *stack; void *stack;
atomic_t usage; refcount_t usage;
/* Per task flags (PF_*), defined further below: */ /* Per task flags (PF_*), defined further below: */
unsigned int flags; unsigned int flags;
unsigned int ptrace; unsigned int ptrace;
......
...@@ -88,13 +88,13 @@ extern void sched_exec(void); ...@@ -88,13 +88,13 @@ extern void sched_exec(void);
#define sched_exec() {} #define sched_exec() {}
#endif #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); extern void __put_task_struct(struct task_struct *t);
static inline 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); __put_task_struct(t);
} }
......
...@@ -65,7 +65,7 @@ struct task_struct init_task ...@@ -65,7 +65,7 @@ struct task_struct init_task
#endif #endif
.state = 0, .state = 0,
.stack = init_stack, .stack = init_stack,
.usage = ATOMIC_INIT(2), .usage = REFCOUNT_INIT(2),
.flags = PF_KTHREAD, .flags = PF_KTHREAD,
.prio = MAX_PRIO - 20, .prio = MAX_PRIO - 20,
.static_prio = MAX_PRIO - 20, .static_prio = MAX_PRIO - 20,
......
...@@ -717,7 +717,7 @@ static inline void put_signal_struct(struct signal_struct *sig) ...@@ -717,7 +717,7 @@ static inline void put_signal_struct(struct signal_struct *sig)
void __put_task_struct(struct task_struct *tsk) void __put_task_struct(struct task_struct *tsk)
{ {
WARN_ON(!tsk->exit_state); WARN_ON(!tsk->exit_state);
WARN_ON(atomic_read(&tsk->usage)); WARN_ON(refcount_read(&tsk->usage));
WARN_ON(tsk == current); WARN_ON(tsk == current);
cgroup_free(tsk); cgroup_free(tsk);
...@@ -896,7 +896,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) ...@@ -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 * One for us, one for whoever does the "release_task()" (usually
* parent) * parent)
*/ */
atomic_set(&tsk->usage, 2); refcount_set(&tsk->usage, 2);
#ifdef CONFIG_BLK_DEV_IO_TRACE #ifdef CONFIG_BLK_DEV_IO_TRACE
tsk->btrace_seq = 0; tsk->btrace_seq = 0;
#endif #endif
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment