1 files changed, 58 insertions, 54 deletions

diff --git a/kernel/timer.c b/kernel/timer.c
index 97bf05baade7..8cff36119e4d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -37,7 +37,7 @@
 #include <linux/delay.h>
 #include <linux/tick.h>
 #include <linux/kallsyms.h>
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 
@@ -88,18 +88,6 @@ struct tvec_base boot_tvec_bases;
 EXPORT_SYMBOL(boot_tvec_bases);
 static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
 
-/*
- * Note that all tvec_bases are 2 byte aligned and lower bit of
- * base in timer_list is guaranteed to be zero. Use the LSB to
- * indicate whether the timer is deferrable.
- *
- * A deferrable timer will work normally when the system is busy, but
- * will not cause a CPU to come out of idle just to service it; instead,
- * the timer will be serviced when the CPU eventually wakes up with a
- * subsequent non-deferrable timer.
- */
-#define TBASE_DEFERRABLE_FLAG           (0x1)
-
 /* Functions below help us manage 'deferrable' flag */
 static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
 {
@@ -113,8 +101,7 @@ static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
 
 static inline void timer_set_deferrable(struct timer_list *timer)
 {
-        timer->base = ((struct tvec_base *)((unsigned long)(timer->base) |
-                                       TBASE_DEFERRABLE_FLAG));
+        timer->base = TBASE_MAKE_DEFERRED(timer->base);
 }
 
 static inline void
@@ -343,15 +330,6 @@ void set_timer_slack(struct timer_list *timer, int slack_hz)
 }
 EXPORT_SYMBOL_GPL(set_timer_slack);
 
-
-static inline void set_running_timer(struct tvec_base *base,
-                                        struct timer_list *timer)
-{
-#ifdef CONFIG_SMP
-        base->running_timer = timer;
-#endif
-}
-
 static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
         unsigned long expires = timer->expires;
@@ -426,6 +404,11 @@ static void timer_stats_account_timer(struct timer_list *timer) {}
 
 static struct debug_obj_descr timer_debug_descr;
 
+static void *timer_debug_hint(void *addr)
+{
+        return ((struct timer_list *) addr)->function;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -499,6 +482,7 @@ static int timer_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr timer_debug_descr = {
         .name           = "timer_list",
+        .debug_hint     = timer_debug_hint,
         .fixup_init     = timer_fixup_init,
         .fixup_activate = timer_fixup_activate,
         .fixup_free     = timer_fixup_free,
@@ -765,16 +749,15 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
         unsigned long expires_limit, mask;
         int bit;
 
-        expires_limit = expires;
-
         if (timer->slack >= 0) {
                 expires_limit = expires + timer->slack;
         } else {
-                unsigned long now = jiffies;
+                long delta = expires - jiffies;
+
+                if (delta < 256)
+                        return expires;
 
-                /* No slack, if already expired else auto slack 0.4% */
-                if (time_after(expires, now))
-                        expires_limit = expires + (expires - now)/256;
+                expires_limit = expires + delta / 256;
         }
         mask = expires ^ expires_limit;
         if (mask == 0)
@@ -811,6 +794,8 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
+        expires = apply_slack(timer, expires);
+
         /*
          * This is a common optimization triggered by the
          * networking code - if the timer is re-modified
@@ -819,8 +804,6 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
         if (timer_pending(timer) && timer->expires == expires)
                 return 1;
 
-        expires = apply_slack(timer, expires);
-
         return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
 }
 EXPORT_SYMBOL(mod_timer);
@@ -936,15 +919,12 @@ int del_timer(struct timer_list *timer)
 }
 EXPORT_SYMBOL(del_timer);
 
-#ifdef CONFIG_SMP
 /**
  * try_to_del_timer_sync - Try to deactivate a timer
  * @timer: timer do del
  *
  * This function tries to deactivate a timer. Upon successful (ret >= 0)
  * exit the timer is not queued and the handler is not running on any CPU.
- *
- * It must not be called from interrupt contexts.
  */
 int try_to_del_timer_sync(struct timer_list *timer)
 {
@@ -973,6 +953,7 @@ out:
 }
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
+#ifdef CONFIG_SMP
 /**
  * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
@@ -988,6 +969,25 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
  * add_timer_on(). Upon exit the timer is not queued and the handler is
  * not running on any CPU.
  *
+ * Note: You must not hold locks that are held in interrupt context
+ *   while calling this function. Even if the lock has nothing to do
+ *   with the timer in question.  Here's why:
+ *
+ *    CPU0                             CPU1
+ *    ----                             ----
+ *                                   <SOFTIRQ>
+ *                                   call_timer_fn();
+ *                                     base->running_timer = mytimer;
+ *  spin_lock_irq(somelock);
+ *                                     <IRQ>
+ *                                        spin_lock(somelock);
+ *  del_timer_sync(mytimer);
+ *   while (base->running_timer == mytimer);
+ *
+ * Now del_timer_sync() will never return and never release somelock.
+ * The interrupt on the other CPU is waiting to grab somelock but
+ * it has interrupted the softirq that CPU0 is waiting to finish.
+ *
  * The function returns whether it has deactivated a pending timer or not.
  */
 int del_timer_sync(struct timer_list *timer)
@@ -995,12 +995,20 @@ int del_timer_sync(struct timer_list *timer)
 #ifdef CONFIG_LOCKDEP
         unsigned long flags;
 
+        /*
+         * If lockdep gives a backtrace here, please reference
+         * the synchronization rules above.
+         */
         local_irq_save(flags);
         lock_map_acquire(&timer->lockdep_map);
         lock_map_release(&timer->lockdep_map);
         local_irq_restore(flags);
 #endif
-
+        /*
+         * don't use it in hardirq context, because it
+         * could lead to deadlock.
+         */
+        WARN_ON(in_irq());
         for (;;) {
                 int ret = try_to_del_timer_sync(timer);
                 if (ret >= 0)
@@ -1111,7 +1119,7 @@ static inline void __run_timers(struct tvec_base *base)
 
                         timer_stats_account_timer(timer);
 
-                        set_running_timer(base, timer);
+                        base->running_timer = timer;
                         detach_timer(timer, 1);
 
                         spin_unlock_irq(&base->lock);
@@ -1119,7 +1127,7 @@ static inline void __run_timers(struct tvec_base *base)
                         spin_lock_irq(&base->lock);
                 }
         }
-        set_running_timer(base, NULL);
+        base->running_timer = NULL;
         spin_unlock_irq(&base->lock);
 }
 
@@ -1249,9 +1257,15 @@ static unsigned long cmp_next_hrtimer_event(unsigned long now,
  */
 unsigned long get_next_timer_interrupt(unsigned long now)
 {
-        struct tvec_base *base = __get_cpu_var(tvec_bases);
+        struct tvec_base *base = __this_cpu_read(tvec_bases);
         unsigned long expires;
 
+        /*
+         * Pretend that there is no timer pending if the cpu is offline.
+         * Possible pending timers will be migrated later to an active cpu.
+         */
+        if (cpu_is_offline(smp_processor_id()))
+                return now + NEXT_TIMER_MAX_DELTA;
         spin_lock(&base->lock);
         if (time_before_eq(base->next_timer, base->timer_jiffies))
                 base->next_timer = __next_timer_interrupt(base);
@@ -1279,7 +1293,10 @@ void update_process_times(int user_tick)
         run_local_timers();
         rcu_check_callbacks(cpu, user_tick);
         printk_tick();
-        perf_event_do_pending();
+#ifdef CONFIG_IRQ_WORK
+        if (in_irq())
+                irq_work_run();
+#endif
         scheduler_tick();
         run_posix_cpu_timers(p);
 }
@@ -1289,7 +1306,7 @@ void update_process_times(int user_tick)
  */
 static void run_timer_softirq(struct softirq_action *h)
 {
-        struct tvec_base *base = __get_cpu_var(tvec_bases);
+        struct tvec_base *base = __this_cpu_read(tvec_bases);
 
         hrtimer_run_pending();
 
@@ -1306,19 +1323,6 @@ void run_local_timers(void)
         raise_softirq(TIMER_SOFTIRQ);
 }
 
-/*
- * The 64-bit jiffies value is not atomic - you MUST NOT read it
- * without sampling the sequence number in xtime_lock.
- * jiffies is defined in the linker script...
- */
-
-void do_timer(unsigned long ticks)
-{
-        jiffies_64 += ticks;
-        update_wall_time();
-        calc_global_load();
-}
-
 #ifdef __ARCH_WANT_SYS_ALARM
 
 /*