exec: do not abuse ->cred_guard_mutex in threadgroup_lock()

[deliverable/linux.git] / include / linux / sched.h

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a25168f4ab8603a05800484d175856eee9ba48f9..6f950048b6e90fd8e59b2eb376377310a38cc407 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -151,9 +151,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 #define TASK_DEAD              64
 #define TASK_WAKEKILL          128
 #define TASK_WAKING            256
-#define TASK_STATE_MAX         512
+#define TASK_PARKED            512
+#define TASK_STATE_MAX         1024
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW"
+#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
 
 extern char ___assert_task_state[1 - 2*!!(
                sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
@@ -308,7 +309,6 @@ extern signed long schedule_timeout_killable(signed long timeout);
 extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void schedule(void);
 extern void schedule_preempt_disabled(void);
-extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
 
 struct nsproxy;
 struct user_namespace;
@@ -514,7 +514,8 @@ struct signal_struct {
        unsigned int            has_child_subreaper:1;
 
        /* POSIX.1b Interval Timers */
-       struct list_head posix_timers;
+       int                     posix_timer_id;
+       struct list_head        posix_timers;
 
        /* ITIMER_REAL timer for the process */
        struct hrtimer real_timer;
@@ -625,6 +626,7 @@ struct signal_struct {
 #define SIGNAL_STOP_STOPPED    0x00000001 /* job control stop in effect */
 #define SIGNAL_STOP_CONTINUED  0x00000002 /* SIGCONT since WCONTINUED reap */
 #define SIGNAL_GROUP_EXIT      0x00000004 /* group exit in progress */
+#define SIGNAL_GROUP_COREDUMP  0x00000008 /* coredump in progress */
 /*
  * Pending notifications to parent.
  */
@@ -1628,7 +1630,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define PF_SWAPWRITE   0x00800000      /* Allowed to write to swap */
 #define PF_SPREAD_PAGE 0x01000000      /* Spread page cache over cpuset */
 #define PF_SPREAD_SLAB 0x02000000      /* Spread some slab caches over cpuset */
-#define PF_THREAD_BOUND        0x04000000      /* Thread bound to specific cpu */
+#define PF_NO_SETAFFINITY 0x04000000   /* Userland is not allowed to meddle with cpus_allowed */
 #define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
 #define PF_MEMPOLICY   0x10000000      /* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER        0x20000000      /* Thread belongs to the rt mutex tester */
@@ -2247,27 +2249,18 @@ static inline void threadgroup_change_end(struct task_struct *tsk)
  *
  * Lock the threadgroup @tsk belongs to.  No new task is allowed to enter
  * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
- * perform exec.  This is useful for cases where the threadgroup needs to
- * stay stable across blockable operations.
+ * change ->group_leader/pid.  This is useful for cases where the threadgroup
+ * needs to stay stable across blockable operations.
  *
  * fork and exit paths explicitly call threadgroup_change_{begin|end}() for
  * synchronization.  While held, no new task will be added to threadgroup
  * and no existing live task will have its PF_EXITING set.
  *
- * During exec, a task goes and puts its thread group through unusual
- * changes.  After de-threading, exclusive access is assumed to resources
- * which are usually shared by tasks in the same group - e.g. sighand may
- * be replaced with a new one.  Also, the exec'ing task takes over group
- * leader role including its pid.  Exclude these changes while locked by
- * grabbing cred_guard_mutex which is used to synchronize exec path.
+ * de_thread() does threadgroup_change_{begin|end}() when a non-leader
+ * sub-thread becomes a new leader.
  */
 static inline void threadgroup_lock(struct task_struct *tsk)
 {
-       /*
-        * exec uses exit for de-threading nesting group_rwsem inside
-        * cred_guard_mutex. Grab cred_guard_mutex first.
-        */
-       mutex_lock(&tsk->signal->cred_guard_mutex);
        down_write(&tsk->signal->group_rwsem);
 }
 
@@ -2280,7 +2273,6 @@ static inline void threadgroup_lock(struct task_struct *tsk)
 static inline void threadgroup_unlock(struct task_struct *tsk)
 {
        up_write(&tsk->signal->group_rwsem);
-       mutex_unlock(&tsk->signal->cred_guard_mutex);
 }
 #else
 static inline void threadgroup_change_begin(struct task_struct *tsk) {}
@@ -2456,6 +2448,47 @@ static inline int spin_needbreak(spinlock_t *lock)
 #endif
 }
 
+/*
+ * Idle thread specific functions to determine the need_resched
+ * polling state. We have two versions, one based on TS_POLLING in
+ * thread_info.status and one based on TIF_POLLING_NRFLAG in
+ * thread_info.flags
+ */
+#ifdef TS_POLLING
+static inline int tsk_is_polling(struct task_struct *p)
+{
+       return task_thread_info(p)->status & TS_POLLING;
+}
+static inline void current_set_polling(void)
+{
+       current_thread_info()->status |= TS_POLLING;
+}
+
+static inline void current_clr_polling(void)
+{
+       current_thread_info()->status &= ~TS_POLLING;
+       smp_mb__after_clear_bit();
+}
+#elif defined(TIF_POLLING_NRFLAG)
+static inline int tsk_is_polling(struct task_struct *p)
+{
+       return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
+}
+static inline void current_set_polling(void)
+{
+       set_thread_flag(TIF_POLLING_NRFLAG);
+}
+
+static inline void current_clr_polling(void)
+{
+       clear_thread_flag(TIF_POLLING_NRFLAG);
+}
+#else
+static inline int tsk_is_polling(struct task_struct *p) { return 0; }
+static inline void current_set_polling(void) { }
+static inline void current_clr_polling(void) { }
+#endif
+
 /*
  * Thread group CPU time accounting.
  */