1 files changed, 144 insertions, 59 deletions

diff --git a/kernel/timer.c b/kernel/timer.c
index dee3f641a7a7..cffffad01c31 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -491,14 +491,18 @@ static inline void debug_timer_free(struct timer_list *timer)
         debug_object_free(timer, &timer_debug_descr);
 }
 
-static void __init_timer(struct timer_list *timer);
+static void __init_timer(struct timer_list *timer,
+                         const char *name,
+                         struct lock_class_key *key);
 
-void init_timer_on_stack(struct timer_list *timer)
+void init_timer_on_stack_key(struct timer_list *timer,
+                             const char *name,
+                             struct lock_class_key *key)
 {
         debug_object_init_on_stack(timer, &timer_debug_descr);
-        __init_timer(timer);
+        __init_timer(timer, name, key);
 }
-EXPORT_SYMBOL_GPL(init_timer_on_stack);
+EXPORT_SYMBOL_GPL(init_timer_on_stack_key);
 
 void destroy_timer_on_stack(struct timer_list *timer)
 {
@@ -512,7 +516,9 @@ static inline void debug_timer_activate(struct timer_list *timer) { }
 static inline void debug_timer_deactivate(struct timer_list *timer) { }
 #endif
 
-static void __init_timer(struct timer_list *timer)
+static void __init_timer(struct timer_list *timer,
+                         const char *name,
+                         struct lock_class_key *key)
 {
         timer->entry.next = NULL;
         timer->base = __raw_get_cpu_var(tvec_bases);
@@ -521,28 +527,36 @@ static void __init_timer(struct timer_list *timer)
         timer->start_pid = -1;
         memset(timer->start_comm, 0, TASK_COMM_LEN);
 #endif
+        lockdep_init_map(&timer->lockdep_map, name, key, 0);
 }
 
 /**
- * init_timer - initialize a timer.
+ * init_timer_key - initialize a timer
  * @timer: the timer to be initialized
+ * @name: name of the timer
+ * @key: lockdep class key of the fake lock used for tracking timer
+ *       sync lock dependencies
  *
- * init_timer() must be done to a timer prior calling *any* of the
+ * init_timer_key() must be done to a timer prior calling *any* of the
  * other timer functions.
  */
-void init_timer(struct timer_list *timer)
+void init_timer_key(struct timer_list *timer,
+                    const char *name,
+                    struct lock_class_key *key)
 {
         debug_timer_init(timer);
-        __init_timer(timer);
+        __init_timer(timer, name, key);
 }
-EXPORT_SYMBOL(init_timer);
+EXPORT_SYMBOL(init_timer_key);
 
-void init_timer_deferrable(struct timer_list *timer)
+void init_timer_deferrable_key(struct timer_list *timer,
+                               const char *name,
+                               struct lock_class_key *key)
 {
-        init_timer(timer);
+        init_timer_key(timer, name, key);
         timer_set_deferrable(timer);
 }
-EXPORT_SYMBOL(init_timer_deferrable);
+EXPORT_SYMBOL(init_timer_deferrable_key);
 
 static inline void detach_timer(struct timer_list *timer,
                                 int clear_pending)
@@ -589,11 +603,14 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer,
         }
 }
 
-int __mod_timer(struct timer_list *timer, unsigned long expires)
+static inline int
+__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 {
         struct tvec_base *base, *new_base;
         unsigned long flags;
-        int ret = 0;
+        int ret;
+
+        ret = 0;
 
         timer_stats_timer_set_start_info(timer);
         BUG_ON(!timer->function);
@@ -603,6 +620,9 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
         if (timer_pending(timer)) {
                 detach_timer(timer, 0);
                 ret = 1;
+        } else {
+                if (pending_only)
+                        goto out_unlock;
         }
 
         debug_timer_activate(timer);
@@ -629,42 +649,28 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
 
         timer->expires = expires;
         internal_add_timer(base, timer);
+
+out_unlock:
         spin_unlock_irqrestore(&base->lock, flags);
 
         return ret;
 }
 
-EXPORT_SYMBOL(__mod_timer);
-
 /**
- * add_timer_on - start a timer on a particular CPU
- * @timer: the timer to be added
- * @cpu: the CPU to start it on
+ * mod_timer_pending - modify a pending timer's timeout
+ * @timer: the pending timer to be modified
+ * @expires: new timeout in jiffies
  *
- * This is not very scalable on SMP. Double adds are not possible.
+ * mod_timer_pending() is the same for pending timers as mod_timer(),
+ * but will not re-activate and modify already deleted timers.
+ *
+ * It is useful for unserialized use of timers.
  */
-void add_timer_on(struct timer_list *timer, int cpu)
+int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 {
-        struct tvec_base *base = per_cpu(tvec_bases, cpu);
-        unsigned long flags;
-
-        timer_stats_timer_set_start_info(timer);
-        BUG_ON(timer_pending(timer) || !timer->function);
-        spin_lock_irqsave(&base->lock, flags);
-        timer_set_base(timer, base);
-        debug_timer_activate(timer);
-        internal_add_timer(base, timer);
-        /*
-         * Check whether the other CPU is idle and needs to be
-         * triggered to reevaluate the timer wheel when nohz is
-         * active. We are protected against the other CPU fiddling
-         * with the timer by holding the timer base lock. This also
-         * makes sure that a CPU on the way to idle can not evaluate
-         * the timer wheel.
-         */
-        wake_up_idle_cpu(cpu);
-        spin_unlock_irqrestore(&base->lock, flags);
+        return __mod_timer(timer, expires, true);
 }
+EXPORT_SYMBOL(mod_timer_pending);
 
 /**
  * mod_timer - modify a timer's timeout
@@ -688,9 +694,6 @@ void add_timer_on(struct timer_list *timer, int cpu)
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
-        BUG_ON(!timer->function);
-
-        timer_stats_timer_set_start_info(timer);
         /*
          * This is a common optimization triggered by the
          * networking code - if the timer is re-modified
@@ -699,12 +702,62 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
         if (timer->expires == expires && timer_pending(timer))
                 return 1;
 
-        return __mod_timer(timer, expires);
+        return __mod_timer(timer, expires, false);
 }
-
 EXPORT_SYMBOL(mod_timer);
 
 /**
+ * add_timer - start a timer
+ * @timer: the timer to be added
+ *
+ * The kernel will do a ->function(->data) callback from the
+ * timer interrupt at the ->expires point in the future. The
+ * current time is 'jiffies'.
+ *
+ * The timer's ->expires, ->function (and if the handler uses it, ->data)
+ * fields must be set prior calling this function.
+ *
+ * Timers with an ->expires field in the past will be executed in the next
+ * timer tick.
+ */
+void add_timer(struct timer_list *timer)
+{
+        BUG_ON(timer_pending(timer));
+        mod_timer(timer, timer->expires);
+}
+EXPORT_SYMBOL(add_timer);
+
+/**
+ * add_timer_on - start a timer on a particular CPU
+ * @timer: the timer to be added
+ * @cpu: the CPU to start it on
+ *
+ * This is not very scalable on SMP. Double adds are not possible.
+ */
+void add_timer_on(struct timer_list *timer, int cpu)
+{
+        struct tvec_base *base = per_cpu(tvec_bases, cpu);
+        unsigned long flags;
+
+        timer_stats_timer_set_start_info(timer);
+        BUG_ON(timer_pending(timer) || !timer->function);
+        spin_lock_irqsave(&base->lock, flags);
+        timer_set_base(timer, base);
+        debug_timer_activate(timer);
+        internal_add_timer(base, timer);
+        /*
+         * Check whether the other CPU is idle and needs to be
+         * triggered to reevaluate the timer wheel when nohz is
+         * active. We are protected against the other CPU fiddling
+         * with the timer by holding the timer base lock. This also
+         * makes sure that a CPU on the way to idle can not evaluate
+         * the timer wheel.
+         */
+        wake_up_idle_cpu(cpu);
+        spin_unlock_irqrestore(&base->lock, flags);
+}
+
+/**
  * del_timer - deactive a timer.
  * @timer: the timer to be deactivated
  *
@@ -733,7 +786,6 @@ int del_timer(struct timer_list *timer)
 
         return ret;
 }
-
 EXPORT_SYMBOL(del_timer);
 
 #ifdef CONFIG_SMP
@@ -767,7 +819,6 @@ out:
 
         return ret;
 }
-
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
 /**
@@ -789,6 +840,15 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
  */
 int del_timer_sync(struct timer_list *timer)
 {
+#ifdef CONFIG_LOCKDEP
+        unsigned long flags;
+
+        local_irq_save(flags);
+        lock_map_acquire(&timer->lockdep_map);
+        lock_map_release(&timer->lockdep_map);
+        local_irq_restore(flags);
+#endif
+
         for (;;) {
                 int ret = try_to_del_timer_sync(timer);
                 if (ret >= 0)
@@ -796,7 +856,6 @@ int del_timer_sync(struct timer_list *timer)
                 cpu_relax();
         }
 }
-
 EXPORT_SYMBOL(del_timer_sync);
 #endif
 
@@ -861,10 +920,36 @@ static inline void __run_timers(struct tvec_base *base)
 
                         set_running_timer(base, timer);
                         detach_timer(timer, 1);
+
                         spin_unlock_irq(&base->lock);
                         {
                                 int preempt_count = preempt_count();
+
+#ifdef CONFIG_LOCKDEP
+                                /*
+                                 * It is permissible to free the timer from
+                                 * inside the function that is called from
+                                 * it, this we need to take into account for
+                                 * lockdep too. To avoid bogus "held lock
+                                 * freed" warnings as well as problems when
+                                 * looking into timer->lockdep_map, make a
+                                 * copy and use that here.
+                                 */
+                                struct lockdep_map lockdep_map =
+                                        timer->lockdep_map;
+#endif
+                                /*
+                                 * Couple the lock chain with the lock chain at
+                                 * del_timer_sync() by acquiring the lock_map
+                                 * around the fn() call here and in
+                                 * del_timer_sync().
+                                 */
+                                lock_map_acquire(&lockdep_map);
+
                                 fn(data);
+
+                                lock_map_release(&lockdep_map);
+
                                 if (preempt_count != preempt_count()) {
                                         printk(KERN_ERR "huh, entered %p "
                                                "with preempt_count %08x, exited"
@@ -1129,7 +1214,7 @@ void do_timer(unsigned long ticks)
  * For backwards compatibility?  This can be done in libc so Alpha
  * and all newer ports shouldn't need it.
  */
-asmlinkage unsigned long sys_alarm(unsigned int seconds)
+SYSCALL_DEFINE1(alarm, unsigned int, seconds)
 {
         return alarm_setitimer(seconds);
 }
@@ -1152,7 +1237,7 @@ asmlinkage unsigned long sys_alarm(unsigned int seconds)
  *
  * This is SMP safe as current->tgid does not change.
  */
-asmlinkage long sys_getpid(void)
+SYSCALL_DEFINE0(getpid)
 {
         return task_tgid_vnr(current);
 }
@@ -1163,7 +1248,7 @@ asmlinkage long sys_getpid(void)
  * value of ->real_parent under rcu_read_lock(), see
  * release_task()->call_rcu(delayed_put_task_struct).
  */
-asmlinkage long sys_getppid(void)
+SYSCALL_DEFINE0(getppid)
 {
         int pid;
 
@@ -1174,25 +1259,25 @@ asmlinkage long sys_getppid(void)
         return pid;
 }
 
-asmlinkage long sys_getuid(void)
+SYSCALL_DEFINE0(getuid)
 {
         /* Only we change this so SMP safe */
         return current_uid();
 }
 
-asmlinkage long sys_geteuid(void)
+SYSCALL_DEFINE0(geteuid)
 {
         /* Only we change this so SMP safe */
         return current_euid();
 }
 
-asmlinkage long sys_getgid(void)
+SYSCALL_DEFINE0(getgid)
 {
         /* Only we change this so SMP safe */
         return current_gid();
 }
 
-asmlinkage long sys_getegid(void)
+SYSCALL_DEFINE0(getegid)
 {
         /* Only we change this so SMP safe */
         return  current_egid();
@@ -1268,7 +1353,7 @@ signed long __sched schedule_timeout(signed long timeout)
         expire = timeout + jiffies;
 
         setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
-        __mod_timer(&timer, expire);
+        __mod_timer(&timer, expire, false);
         schedule();
         del_singleshot_timer_sync(&timer);
 
@@ -1308,7 +1393,7 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout)
 EXPORT_SYMBOL(schedule_timeout_uninterruptible);
 
 /* Thread ID - the internal kernel "pid" */
-asmlinkage long sys_gettid(void)
+SYSCALL_DEFINE0(gettid)
 {
         return task_pid_vnr(current);
 }
@@ -1400,7 +1485,7 @@ out:
         return 0;
 }
 
-asmlinkage long sys_sysinfo(struct sysinfo __user *info)
+SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info)
 {
         struct sysinfo val;