Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer fixes from Thomas Gleixner:
 "Three fixlets from the timer departement:

   - Update the timekeeper before updating vsyscall and pvclock.  This
     fixes the kvm-clock regression reported by Chris and Paolo.

   - Use the proper irq work interface from NMI.  This fixes the
     regression reported by Catalin and Dave.

   - Clarify the compat_nanosleep error handling mechanism to avoid
     future confusion"

* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  timekeeping: Update timekeeper before updating vsyscall and pvclock
  compat: nanosleep: Clarify error handling
  nohz: Restore NMI safe local irq work for local nohz kick

3 files changed, 38 insertions, 5 deletions

diff --git a/kernel/compat.c b/kernel/compat.c
index 633394f442f8..ebb3c369d03d 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -226,7 +226,7 @@ static long compat_nanosleep_restart(struct restart_block *restart)
         ret = hrtimer_nanosleep_restart(restart);
         set_fs(oldfs);
 
-        if (ret) {
+        if (ret == -ERESTART_RESTARTBLOCK) {
                 rmtp = restart->nanosleep.compat_rmtp;
 
                 if (rmtp && compat_put_timespec(&rmt, rmtp))
@@ -256,7 +256,26 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
                                 HRTIMER_MODE_REL, CLOCK_MONOTONIC);
         set_fs(oldfs);
 
-        if (ret) {
+        /*
+         * hrtimer_nanosleep() can only return 0 or
+         * -ERESTART_RESTARTBLOCK here because:
+         *
+         * - we call it with HRTIMER_MODE_REL and therefor exclude the
+         *   -ERESTARTNOHAND return path.
+         *
+         * - we supply the rmtp argument from the task stack (due to
+         *   the necessary compat conversion. So the update cannot
+         *   fail, which excludes the -EFAULT return path as well. If
+         *   it fails nevertheless we have a bigger problem and wont
+         *   reach this place anymore.
+         *
+         * - if the return value is 0, we do not have to update rmtp
+         *    because there is no remaining time.
+         *
+         * We check for -ERESTART_RESTARTBLOCK nevertheless if the
+         * core implementation decides to return random nonsense.
+         */
+        if (ret == -ERESTART_RESTARTBLOCK) {
                 struct restart_block *restart
                         = &current_thread_info()->restart_block;
 
@@ -266,7 +285,6 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
                 if (rmtp && compat_put_timespec(&rmt, rmtp))
                         return -EFAULT;
         }
-
         return ret;
 }
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 99aa6ee3908f..f654a8a298fa 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -225,6 +225,20 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
 };
 
 /*
+ * Kick this CPU if it's full dynticks in order to force it to
+ * re-evaluate its dependency on the tick and restart it if necessary.
+ * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(),
+ * is NMI safe.
+ */
+void tick_nohz_full_kick(void)
+{
+        if (!tick_nohz_full_cpu(smp_processor_id()))
+                return;
+
+        irq_work_queue(&__get_cpu_var(nohz_full_kick_work));
+}
+
+/*
  * Kick the CPU if it's full dynticks in order to force it to
  * re-evaluate its dependency on the tick and restart it if necessary.
  */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index fb4a9c2cf8d9..ec1791fae965 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -442,11 +442,12 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
                 tk->ntp_error = 0;
                 ntp_clear();
         }
-        update_vsyscall(tk);
-        update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
 
         tk_update_ktime_data(tk);
 
+        update_vsyscall(tk);
+        update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
+
         if (action & TK_MIRROR)
                 memcpy(&shadow_timekeeper, &tk_core.timekeeper,
                        sizeof(tk_core.timekeeper));