20 files changed, 204 insertions, 130 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 7dc8788cfd52..3a73f995a81e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1035,6 +1035,11 @@ static void cgroup_get(struct cgroup *cgrp)
         css_get(&cgrp->self);
 }
 
+static bool cgroup_tryget(struct cgroup *cgrp)
+{
+        return css_tryget(&cgrp->self);
+}
+
 static void cgroup_put(struct cgroup *cgrp)
 {
         css_put(&cgrp->self);
@@ -1147,7 +1152,8 @@ static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn)
          * protection against removal.  Ensure @cgrp stays accessible and
          * break the active_ref protection.
          */
-        cgroup_get(cgrp);
+        if (!cgroup_tryget(cgrp))
+                return NULL;
         kernfs_break_active_protection(kn);
 
         mutex_lock(&cgroup_mutex);
@@ -3271,8 +3277,17 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 {
         struct cftype *cft;
 
-        for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
-                cft->flags |= __CFTYPE_NOT_ON_DFL;
+        /*
+         * If legacy_flies_on_dfl, we want to show the legacy files on the
+         * dfl hierarchy but iff the target subsystem hasn't been updated
+         * for the dfl hierarchy yet.
+         */
+        if (!cgroup_legacy_files_on_dfl ||
+            ss->dfl_cftypes != ss->legacy_cftypes) {
+                for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
+                        cft->flags |= __CFTYPE_NOT_ON_DFL;
+        }
+
         return cgroup_add_cftypes(ss, cfts);
 }
 
@@ -3970,7 +3985,6 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 
         l = cgroup_pidlist_find_create(cgrp, type);
         if (!l) {
-                mutex_unlock(&cgrp->pidlist_mutex);
                 pidlist_free(array);
                 return -ENOMEM;
         }
@@ -4387,6 +4401,15 @@ static void css_release_work_fn(struct work_struct *work)
                 /* cgroup release path */
                 cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
                 cgrp->id = -1;
+
+                /*
+                 * There are two control paths which try to determine
+                 * cgroup from dentry without going through kernfs -
+                 * cgroupstats_build() and css_tryget_online_from_dir().
+                 * Those are supported by RCU protecting clearing of
+                 * cgrp->kn->priv backpointer.
+                 */
+                RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
         }
 
         mutex_unlock(&cgroup_mutex);
@@ -4543,6 +4566,11 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
         struct cftype *base_files;
         int ssid, ret;
 
+        /* Do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable.
+         */
+        if (strchr(name, '\n'))
+                return -EINVAL;
+
         parent = cgroup_kn_lock_live(parent_kn);
         if (!parent)
                 return -ENODEV;
@@ -4820,16 +4848,6 @@ static int cgroup_rmdir(struct kernfs_node *kn)
 
         cgroup_kn_unlock(kn);
 
-        /*
-         * There are two control paths which try to determine cgroup from
-         * dentry without going through kernfs - cgroupstats_build() and
-         * css_tryget_online_from_dir().  Those are supported by RCU
-         * protecting clearing of cgrp->kn->priv backpointer, which should
-         * happen after all files under it have been removed.
-         */
-        if (!ret)
-                RCU_INIT_POINTER(*(void __rcu __force **)&kn->priv, NULL);
-
         cgroup_put(cgrp);
         return ret;
 }
@@ -5416,7 +5434,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
         /*
          * This path doesn't originate from kernfs and @kn could already
          * have been or be removed at any point.  @kn->priv is RCU
-         * protected for this access.  See cgroup_rmdir() for details.
+         * protected for this access.  See css_release_work_fn() for details.
          */
         cgrp = rcu_dereference(kn->priv);
         if (cgrp)
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/cpuset.c b/kernel/cpuset.c
index 22874d7cf2c0..52cb04c993b7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -365,13 +365,14 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs,
                                         struct task_struct *tsk)
 {
         if (is_spread_page(cs))
-                tsk->flags |= PF_SPREAD_PAGE;
+                task_set_spread_page(tsk);
         else
-                tsk->flags &= ~PF_SPREAD_PAGE;
+                task_clear_spread_page(tsk);
+
         if (is_spread_slab(cs))
-                tsk->flags |= PF_SPREAD_SLAB;
+                task_set_spread_slab(tsk);
         else
-                tsk->flags &= ~PF_SPREAD_SLAB;
+                task_clear_spread_slab(tsk);
 }
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f9c1ed002dbc..963bf139e2b2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1524,6 +1524,11 @@ retry:
          */
         if (ctx->is_active) {
                 raw_spin_unlock_irq(&ctx->lock);
+                /*
+                 * Reload the task pointer, it might have been changed by
+                 * a concurrent perf_event_context_sched_out().
+                 */
+                task = ctx->task;
                 goto retry;
         }
 
@@ -1967,6 +1972,11 @@ retry:
          */
         if (ctx->is_active) {
                 raw_spin_unlock_irq(&ctx->lock);
+                /*
+                 * Reload the task pointer, it might have been changed by
+                 * a concurrent perf_event_context_sched_out().
+                 */
+                task = ctx->task;
                 goto retry;
         }
 
@@ -7938,8 +7948,10 @@ int perf_event_init_task(struct task_struct *child)
 
         for_each_task_context_nr(ctxn) {
                 ret = perf_event_init_context(child, ctxn);
-                if (ret)
+                if (ret) {
+                        perf_event_free_task(child);
                         return ret;
+                }
         }
 
         return 0;
diff --git a/kernel/fork.c b/kernel/fork.c
index 0cf9cdb6e491..a91e47d86de2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1360,7 +1360,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                 goto bad_fork_cleanup_policy;
         retval = audit_alloc(p);
         if (retval)
-                goto bad_fork_cleanup_policy;
+                goto bad_fork_cleanup_perf;
         /* copy all the process information */
         shm_init_task(p);
         retval = copy_semundo(clone_flags, p);
@@ -1566,8 +1566,9 @@ bad_fork_cleanup_semundo:
         exit_sem(p);
 bad_fork_cleanup_audit:
         audit_free(p);
-bad_fork_cleanup_policy:
+bad_fork_cleanup_perf:
         perf_event_free_task(p);
+bad_fork_cleanup_policy:
 #ifdef CONFIG_NUMA
         mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
diff --git a/kernel/futex.c b/kernel/futex.c
index d3a9d946d0b7..815d7af2ffe8 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2592,6 +2592,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
          * shared futexes. We need to compare the keys:
          */
         if (match_futex(&q.key, &key2)) {
+                queue_unlock(hb);
                 ret = -EINVAL;
                 goto out_put_keys;
         }
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index a2b28a2fd7b1..6223fab9a9d2 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -517,6 +517,7 @@ out:
                 chip->irq_eoi(&desc->irq_data);
         raw_spin_unlock(&desc->lock);
 }
+EXPORT_SYMBOL_GPL(handle_fasteoi_irq);
 
 /**
  *      handle_edge_irq - edge type IRQ handler
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index e30ac0fe61c3..0aa69ea1d8fd 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -44,11 +44,12 @@ static long kptr_obfuscate(long v, int type)
  */
 static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type)
 {
-        long ret;
+        long t1, t2;
 
-        ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type);
+        t1 = kptr_obfuscate((long)v1, type);
+        t2 = kptr_obfuscate((long)v2, type);
 
-        return (ret < 0) | ((ret > 0) << 1);
+        return (t1 < t2) | ((t1 > t2) << 1);
 }
 
 /* The caller must have pinned the task */
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 5d49dcac2537..2df883a9d3cb 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -179,6 +179,7 @@ extern void swsusp_show_speed(struct timeval *, struct timeval *,
 
 #ifdef CONFIG_SUSPEND
 /* kernel/power/suspend.c */
+extern const char *pm_labels[];
 extern const char *pm_states[];
 
 extern int suspend_devices_and_enter(suspend_state_t state);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index c4b8093c80b3..f1604d8cf489 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -725,14 +725,6 @@ static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn)
         clear_bit(bit, addr);
 }
 
-static void memory_bm_clear_current(struct memory_bitmap *bm)
-{
-        int bit;
-
-        bit = max(bm->cur.node_bit - 1, 0);
-        clear_bit(bit, bm->cur.node->data);
-}
-
 static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
         void *addr;
@@ -1341,35 +1333,23 @@ static struct memory_bitmap copy_bm;
 
 void swsusp_free(void)
 {
-        unsigned long fb_pfn, fr_pfn;
-
-        memory_bm_position_reset(forbidden_pages_map);
-        memory_bm_position_reset(free_pages_map);
-
-loop:
-        fr_pfn = memory_bm_next_pfn(free_pages_map);
-        fb_pfn = memory_bm_next_pfn(forbidden_pages_map);
-
-        /*
-         * Find the next bit set in both bitmaps. This is guaranteed to
-         * terminate when fb_pfn == fr_pfn == BM_END_OF_MAP.
-         */
-        do {
-                if (fb_pfn < fr_pfn)
-                        fb_pfn = memory_bm_next_pfn(forbidden_pages_map);
-                if (fr_pfn < fb_pfn)
-                        fr_pfn = memory_bm_next_pfn(free_pages_map);
-        } while (fb_pfn != fr_pfn);
-
-        if (fr_pfn != BM_END_OF_MAP && pfn_valid(fr_pfn)) {
-                struct page *page = pfn_to_page(fr_pfn);
+        struct zone *zone;
+        unsigned long pfn, max_zone_pfn;
 
-                memory_bm_clear_current(forbidden_pages_map);
-                memory_bm_clear_current(free_pages_map);
-                __free_page(page);
-                goto loop;
+        for_each_populated_zone(zone) {
+                max_zone_pfn = zone_end_pfn(zone);
+                for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
+                        if (pfn_valid(pfn)) {
+                                struct page *page = pfn_to_page(pfn);
+
+                                if (swsusp_page_is_forbidden(page) &&
+                                    swsusp_page_is_free(page)) {
+                                        swsusp_unset_page_forbidden(page);
+                                        swsusp_unset_page_free(page);
+                                        __free_page(page);
+                                }
+                        }
         }
-
         nr_copy_pages = 0;
         nr_meta_pages = 0;
         restore_pblist = NULL;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 6dadb25cb0d8..18c62195660f 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -31,7 +31,7 @@
 
 #include "power.h"
 
-static const char *pm_labels[] = { "mem", "standby", "freeze", };
+const char *pm_labels[] = { "mem", "standby", "freeze", NULL };
 const char *pm_states[PM_SUSPEND_MAX];
 
 static const struct platform_suspend_ops *suspend_ops;
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 2f524928b6aa..bd91bc177c93 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -129,20 +129,20 @@ static int __init has_wakealarm(struct device *dev, const void *data)
  * at startup time.  They're normally disabled, for faster boot and because
  * we can't know which states really work on this particular system.
  */
-static suspend_state_t test_state __initdata = PM_SUSPEND_ON;
+static const char *test_state_label __initdata;
 
 static char warn_bad_state[] __initdata =
         KERN_WARNING "PM: can't test '%s' suspend state\n";
 
 static int __init setup_test_suspend(char *value)
 {
-        suspend_state_t i;
+        int i;
 
         /* "=mem" ==> "mem" */
         value++;
-        for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
-                if (!strcmp(pm_states[i], value)) {
-                        test_state = i;
+        for (i = 0; pm_labels[i]; i++)
+                if (!strcmp(pm_labels[i], value)) {
+                        test_state_label = pm_labels[i];
                         return 0;
                 }
 
@@ -158,13 +158,21 @@ static int __init test_suspend(void)
 
         struct rtc_device       *rtc = NULL;
         struct device           *dev;
+        suspend_state_t test_state;
 
         /* PM is initialized by now; is that state testable? */
-        if (test_state == PM_SUSPEND_ON)
-                goto done;
-        if (!pm_states[test_state]) {
-                printk(warn_bad_state, pm_states[test_state]);
-                goto done;
+        if (!test_state_label)
+                return 0;
+
+        for (test_state = PM_SUSPEND_MIN; test_state < PM_SUSPEND_MAX; test_state++) {
+                const char *state_label = pm_states[test_state];
+
+                if (state_label && !strcmp(test_state_label, state_label))
+                        break;
+        }
+        if (test_state == PM_SUSPEND_MAX) {
+                printk(warn_bad_state, test_state_label);
+                return 0;
         }
 
         /* RTCs have initialized by now too ... can we use one? */
@@ -173,13 +181,12 @@ static int __init test_suspend(void)
                 rtc = rtc_class_open(dev_name(dev));
         if (!rtc) {
                 printk(warn_no_rtc);
-                goto done;
+                return 0;
         }
 
         /* go for it */
         test_wakealarm(rtc, test_state);
         rtc_class_close(rtc);
-done:
         return 0;
 }
 late_initcall(test_suspend);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index e04c455a0e38..1ce770687ea8 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1665,15 +1665,15 @@ asmlinkage int vprintk_emit(int facility, int level,
         raw_spin_lock(&logbuf_lock);
         logbuf_cpu = this_cpu;
 
-        if (recursion_bug) {
+        if (unlikely(recursion_bug)) {
                 static const char recursion_msg[] =
                         "BUG: recent printk recursion!";
 
                 recursion_bug = 0;
-                text_len = strlen(recursion_msg);
                 /* emit KERN_CRIT message */
                 printed_len += log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0,
-                                         NULL, 0, recursion_msg, text_len);
+                                         NULL, 0, recursion_msg,
+                                         strlen(recursion_msg));
         }
 
         /*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 71e64c718f75..6a86eb7bac45 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -358,7 +358,7 @@ struct rcu_data {
         struct rcu_head **nocb_gp_tail;
         long nocb_gp_count;
         long nocb_gp_count_lazy;
-        bool nocb_leader_wake;          /* Is the nocb leader thread awake? */
+        bool nocb_leader_sleep;         /* Is the nocb leader thread asleep? */
         struct rcu_data *nocb_next_follower;
                                         /* Next follower in wakeup chain. */
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 00dc411e9676..a7997e272564 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2074,9 +2074,9 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
 
         if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
                 return;
-        if (!ACCESS_ONCE(rdp_leader->nocb_leader_wake) || force) {
+        if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) {
                 /* Prior xchg orders against prior callback enqueue. */
-                ACCESS_ONCE(rdp_leader->nocb_leader_wake) = true;
+                ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false;
                 wake_up(&rdp_leader->nocb_wq);
         }
 }
@@ -2253,7 +2253,7 @@ wait_again:
         if (!rcu_nocb_poll) {
                 trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
                 wait_event_interruptible(my_rdp->nocb_wq,
-                                         ACCESS_ONCE(my_rdp->nocb_leader_wake));
+                                !ACCESS_ONCE(my_rdp->nocb_leader_sleep));
                 /* Memory barrier handled by smp_mb() calls below and repoll. */
         } else if (firsttime) {
                 firsttime = false; /* Don't drown trace log with "Poll"! */
@@ -2292,12 +2292,12 @@ wait_again:
                 schedule_timeout_interruptible(1);
 
                 /* Rescan in case we were a victim of memory ordering. */
-                my_rdp->nocb_leader_wake = false;
-                smp_mb();  /* Ensure _wake false before scan. */
+                my_rdp->nocb_leader_sleep = true;
+                smp_mb();  /* Ensure _sleep true before scan. */
                 for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower)
                         if (ACCESS_ONCE(rdp->nocb_head)) {
                                 /* Found CB, so short-circuit next wait. */
-                                my_rdp->nocb_leader_wake = true;
+                                my_rdp->nocb_leader_sleep = false;
                                 break;
                         }
                 goto wait_again;
@@ -2307,17 +2307,17 @@ wait_again:
         rcu_nocb_wait_gp(my_rdp);
 
         /*
-         * We left ->nocb_leader_wake set to reduce cache thrashing.
-         * We clear it now, but recheck for new callbacks while
+         * We left ->nocb_leader_sleep unset to reduce cache thrashing.
+         * We set it now, but recheck for new callbacks while
          * traversing our follower list.
          */
-        my_rdp->nocb_leader_wake = false;
-        smp_mb(); /* Ensure _wake false before scan of ->nocb_head. */
+        my_rdp->nocb_leader_sleep = true;
+        smp_mb(); /* Ensure _sleep true before scan of ->nocb_head. */
 
         /* Each pass through the following loop wakes a follower, if needed. */
         for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
                 if (ACCESS_ONCE(rdp->nocb_head))
-                        my_rdp->nocb_leader_wake = true; /* No need to wait. */
+                        my_rdp->nocb_leader_sleep = false;/* No need to sleep.*/
                 if (!rdp->nocb_gp_head)
                         continue; /* No CBs, so no need to wake follower. */
 
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 4aec4a457431..a7077d3ae52f 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -464,18 +464,26 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid)
 static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
                                                         ktime_t now)
 {
+        unsigned long flags;
         struct k_itimer *ptr = container_of(alarm, struct k_itimer,
                                                 it.alarm.alarmtimer);
-        if (posix_timer_event(ptr, 0) != 0)
-                ptr->it_overrun++;
+        enum alarmtimer_restart result = ALARMTIMER_NORESTART;
+
+        spin_lock_irqsave(&ptr->it_lock, flags);
+        if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) {
+                if (posix_timer_event(ptr, 0) != 0)
+                        ptr->it_overrun++;
+        }
 
         /* Re-add periodic timers */
         if (ptr->it.alarm.interval.tv64) {
                 ptr->it_overrun += alarm_forward(alarm, now,
                                                 ptr->it.alarm.interval);
-                return ALARMTIMER_RESTART;
+                result = ALARMTIMER_RESTART;
         }
-        return ALARMTIMER_NORESTART;
+        spin_unlock_irqrestore(&ptr->it_lock, flags);
+
+        return result;
 }
 
 /**
@@ -541,18 +549,22 @@ static int alarm_timer_create(struct k_itimer *new_timer)
  * @new_timer: k_itimer pointer
  * @cur_setting: itimerspec data to fill
  *
- * Copies the itimerspec data out from the k_itimer
+ * Copies out the current itimerspec data
  */
 static void alarm_timer_get(struct k_itimer *timr,
                                 struct itimerspec *cur_setting)
 {
-        memset(cur_setting, 0, sizeof(struct itimerspec));
+        ktime_t relative_expiry_time =
+                alarm_expires_remaining(&(timr->it.alarm.alarmtimer));
+
+        if (ktime_to_ns(relative_expiry_time) > 0) {
+                cur_setting->it_value = ktime_to_timespec(relative_expiry_time);
+        } else {
+                cur_setting->it_value.tv_sec = 0;
+                cur_setting->it_value.tv_nsec = 0;
+        }
 
-        cur_setting->it_interval =
-                        ktime_to_timespec(timr->it.alarm.interval);
-        cur_setting->it_value =
-                ktime_to_timespec(timr->it.alarm.alarmtimer.node.expires);
-        return;
+        cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval);
 }
 
 /**
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/time.c b/kernel/time/time.c
index f0294ba14634..a9ae20fb0b11 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -559,17 +559,20 @@ EXPORT_SYMBOL(usecs_to_jiffies);
  * that a remainder subtract here would not do the right thing as the
  * resolution values don't fall on second boundries.  I.e. the line:
  * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ * Note that due to the small error in the multiplier here, this
+ * rounding is incorrect for sufficiently large values of tv_nsec, but
+ * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're
+ * OK.
  *
  * Rather, we just shift the bits off the right.
  *
  * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
  * value to a scaled second value.
  */
-unsigned long
-timespec_to_jiffies(const struct timespec *value)
+static unsigned long
+__timespec_to_jiffies(unsigned long sec, long nsec)
 {
-        unsigned long sec = value->tv_sec;
-        long nsec = value->tv_nsec + TICK_NSEC - 1;
+        nsec = nsec + TICK_NSEC - 1;
 
         if (sec >= MAX_SEC_IN_JIFFIES){
                 sec = MAX_SEC_IN_JIFFIES;
@@ -580,6 +583,13 @@ timespec_to_jiffies(const struct timespec *value)
                  (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
 
 }
+
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+        return __timespec_to_jiffies(value->tv_sec, value->tv_nsec);
+}
+
 EXPORT_SYMBOL(timespec_to_jiffies);
 
 void
@@ -596,31 +606,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
 }
 EXPORT_SYMBOL(jiffies_to_timespec);
 
-/* Same for "timeval"
- *
- * Well, almost.  The problem here is that the real system resolution is
- * in nanoseconds and the value being converted is in micro seconds.
- * Also for some machines (those that use HZ = 1024, in-particular),
- * there is a LARGE error in the tick size in microseconds.
-
- * The solution we use is to do the rounding AFTER we convert the
- * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
- * Instruction wise, this should cost only an additional add with carry
- * instruction above the way it was done above.
+/*
+ * We could use a similar algorithm to timespec_to_jiffies (with a
+ * different multiplier for usec instead of nsec). But this has a
+ * problem with rounding: we can't exactly add TICK_NSEC - 1 to the
+ * usec value, since it's not necessarily integral.
+ *
+ * We could instead round in the intermediate scaled representation
+ * (i.e. in units of 1/2^(large scale) jiffies) but that's also
+ * perilous: the scaling introduces a small positive error, which
+ * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1
+ * units to the intermediate before shifting) leads to accidental
+ * overflow and overestimates.
+ *
+ * At the cost of one additional multiplication by a constant, just
+ * use the timespec implementation.
  */
 unsigned long
 timeval_to_jiffies(const struct timeval *value)
 {
-        unsigned long sec = value->tv_sec;
-        long usec = value->tv_usec;
-
-        if (sec >= MAX_SEC_IN_JIFFIES){
-                sec = MAX_SEC_IN_JIFFIES;
-                usec = 0;
-        }
-        return (((u64)sec * SEC_CONVERSION) +
-                (((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
-                 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+        return __timespec_to_jiffies(value->tv_sec,
+                                     value->tv_usec * NSEC_PER_USEC);
 }
 EXPORT_SYMBOL(timeval_to_jiffies);
 
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));
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b38fb2b9e237..2d75c94ae87d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3359,7 +3359,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
         iter->head = cpu_buffer->reader_page->read;
 
         iter->cache_reader_page = iter->head_page;
-        iter->cache_read = iter->head;
+        iter->cache_read = cpu_buffer->read;
 
         if (iter->head)
                 iter->read_stamp = cpu_buffer->read_stamp;