12 files changed, 143 insertions, 22 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 91e53d04b6a9..7b0e23a740ce 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1117,9 +1117,10 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 
                         sleep_time = timeout_start + audit_backlog_wait_time -
                                         jiffies;
-                        if ((long)sleep_time > 0)
+                        if ((long)sleep_time > 0) {
                                 wait_for_auditd(sleep_time);
-                        continue;
+                                continue;
+                        }
                 }
                 if (audit_rate_check() && printk_ratelimit())
                         printk(KERN_WARNING
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 247091bf0587..859c8dfd78a1 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -51,6 +51,15 @@ void context_tracking_user_enter(void)
         unsigned long flags;
 
         /*
+         * Repeat the user_enter() check here because some archs may be calling
+         * this from asm and if no CPU needs context tracking, they shouldn't
+         * go further. Repeat the check here until they support the static key
+         * check.
+         */
+        if (!static_key_false(&context_tracking_enabled))
+                return;
+
+        /*
          * Some contexts may involve an exception occuring in an irq,
          * leading to that nesting:
          * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
@@ -151,6 +160,9 @@ void context_tracking_user_exit(void)
 {
         unsigned long flags;
 
+        if (!static_key_false(&context_tracking_enabled))
+                return;
+
         if (in_interrupt())
                 return;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dd236b66ca3a..d49a9d29334c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3660,6 +3660,26 @@ static void calc_timer_values(struct perf_event *event,
         *running = ctx_time - event->tstamp_running;
 }
 
+static void perf_event_init_userpage(struct perf_event *event)
+{
+        struct perf_event_mmap_page *userpg;
+        struct ring_buffer *rb;
+
+        rcu_read_lock();
+        rb = rcu_dereference(event->rb);
+        if (!rb)
+                goto unlock;
+
+        userpg = rb->user_page;
+
+        /* Allow new userspace to detect that bit 0 is deprecated */
+        userpg->cap_bit0_is_deprecated = 1;
+        userpg->size = offsetof(struct perf_event_mmap_page, __reserved);
+
+unlock:
+        rcu_read_unlock();
+}
+
 void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
 }
@@ -4044,6 +4064,7 @@ again:
         ring_buffer_attach(event, rb);
         rcu_assign_pointer(event->rb, rb);
 
+        perf_event_init_userpage(event);
         perf_event_update_userpage(event);
 
 unlock:
@@ -7213,15 +7234,15 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
                 perf_remove_from_context(event);
                 unaccount_event_cpu(event, src_cpu);
                 put_ctx(src_ctx);
-                list_add(&event->event_entry, &events);
+                list_add(&event->migrate_entry, &events);
         }
         mutex_unlock(&src_ctx->mutex);
 
         synchronize_rcu();
 
         mutex_lock(&dst_ctx->mutex);
-        list_for_each_entry_safe(event, tmp, &events, event_entry) {
-                list_del(&event->event_entry);
+        list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
+                list_del(&event->migrate_entry);
                 if (event->state >= PERF_EVENT_STATE_OFF)
                         event->state = PERF_EVENT_STATE_INACTIVE;
                 account_event_cpu(event, dst_cpu);
diff --git a/kernel/kmod.c b/kernel/kmod.c
index fb326365b694..b086006c59e7 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -571,6 +571,10 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
         DECLARE_COMPLETION_ONSTACK(done);
         int retval = 0;
 
+        if (!sub_info->path) {
+                call_usermodehelper_freeinfo(sub_info);
+                return -EINVAL;
+        }
         helper_lock();
         if (!khelper_wq || usermodehelper_disabled) {
                 retval = -EBUSY;
diff --git a/kernel/params.c b/kernel/params.c
index 81c4e78c8f4c..c00d5b502aa4 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -254,11 +254,11 @@ int parse_args(const char *doing,
 
 
 STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtoul);
+STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtol);
 STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(int, int, "%i", long, kstrtoul);
+STANDARD_PARAM_DEF(int, int, "%i", long, kstrtol);
 STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(long, long, "%li", long, kstrtoul);
+STANDARD_PARAM_DEF(long, long, "%li", long, kstrtol);
 STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul);
 
 int param_set_charp(const char *val, const struct kernel_param *kp)
diff --git a/kernel/pid.c b/kernel/pid.c
index ebe5e80b10f8..9b9a26698144 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -273,6 +273,11 @@ void free_pid(struct pid *pid)
                          */
                         wake_up_process(ns->child_reaper);
                         break;
+                case PIDNS_HASH_ADDING:
+                        /* Handle a fork failure of the first process */
+                        WARN_ON(ns->child_reaper);
+                        ns->nr_hashed = 0;
+                        /* fall through */
                 case 0:
                         schedule_work(&ns->proc_work);
                         break;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 358a146fd4da..98c3b34a4cff 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -743,7 +743,10 @@ int create_basic_memory_bitmaps(void)
         struct memory_bitmap *bm1, *bm2;
         int error = 0;
 
-        BUG_ON(forbidden_pages_map || free_pages_map);
+        if (forbidden_pages_map && free_pages_map)
+                return 0;
+        else
+                BUG_ON(forbidden_pages_map || free_pages_map);
 
         bm1 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL);
         if (!bm1)
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 72e8f4fd616d..957f06164ad1 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -39,6 +39,7 @@ static struct snapshot_data {
         char frozen;
         char ready;
         char platform_support;
+        bool free_bitmaps;
 } snapshot_state;
 
 atomic_t snapshot_device_available = ATOMIC_INIT(1);
@@ -82,6 +83,10 @@ static int snapshot_open(struct inode *inode, struct file *filp)
                 data->swap = -1;
                 data->mode = O_WRONLY;
                 error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+                if (!error) {
+                        error = create_basic_memory_bitmaps();
+                        data->free_bitmaps = !error;
+                }
                 if (error)
                         pm_notifier_call_chain(PM_POST_RESTORE);
         }
@@ -111,6 +116,8 @@ static int snapshot_release(struct inode *inode, struct file *filp)
                 pm_restore_gfp_mask();
                 free_basic_memory_bitmaps();
                 thaw_processes();
+        } else if (data->free_bitmaps) {
+                free_basic_memory_bitmaps();
         }
         pm_notifier_call_chain(data->mode == O_RDONLY ?
                         PM_POST_HIBERNATION : PM_POST_RESTORE);
@@ -231,6 +238,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
                         break;
                 pm_restore_gfp_mask();
                 free_basic_memory_bitmaps();
+                data->free_bitmaps = false;
                 thaw_processes();
                 data->frozen = 0;
                 break;
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 269ed9384cc4..f813b3474646 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -32,7 +32,14 @@ EXPORT_SYMBOL(cad_pid);
 #endif
 enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE;
 
-int reboot_default;
+/*
+ * This variable is used privately to keep track of whether or not
+ * reboot_type is still set to its default value (i.e., reboot= hasn't
+ * been set on the command line).  This is needed so that we can
+ * suppress DMI scanning for reboot quirks.  Without it, it's
+ * impossible to override a faulty reboot quirk without recompiling.
+ */
+int reboot_default = 1;
 int reboot_cpu;
 enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 11cd13667359..7c70201fbc61 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4242,7 +4242,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
         }
 
         if (!se) {
-                cfs_rq->h_load = rq->avg.load_avg_contrib;
+                cfs_rq->h_load = cfs_rq->runnable_load_avg;
                 cfs_rq->last_h_load_update = now;
         }
 
@@ -4823,8 +4823,8 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
                 (busiest->load_per_task * SCHED_POWER_SCALE) /
                 busiest->group_power;
 
-        if (busiest->avg_load - local->avg_load + scaled_busy_load_per_task >=
-            (scaled_busy_load_per_task * imbn)) {
+        if (busiest->avg_load + scaled_busy_load_per_task >=
+            local->avg_load + (scaled_busy_load_per_task * imbn)) {
                 env->imbalance = busiest->load_per_task;
                 return;
         }
@@ -4896,7 +4896,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
          * max load less than avg load(as we skip the groups at or below
          * its cpu_power, while calculating max_load..)
          */
-        if (busiest->avg_load < sds->avg_load) {
+        if (busiest->avg_load <= sds->avg_load ||
+            local->avg_load >= sds->avg_load) {
                 env->imbalance = 0;
                 return fix_small_imbalance(env, sds);
         }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 53cc09ceb0b8..d7d498d8cc4f 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -328,10 +328,19 @@ void irq_enter(void)
 
 static inline void invoke_softirq(void)
 {
-        if (!force_irqthreads)
-                __do_softirq();
-        else
+        if (!force_irqthreads) {
+                /*
+                 * We can safely execute softirq on the current stack if
+                 * it is the irq stack, because it should be near empty
+                 * at this stage. But we have no way to know if the arch
+                 * calls irq_exit() on the irq stack. So call softirq
+                 * in its own stack to prevent from any overrun on top
+                 * of a potentially deep task stack.
+                 */
+                do_softirq();
+        } else {
                 wakeup_softirqd();
+        }
 }
 
 static inline void tick_irq_exit(void)
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 51c4f34d258e..4431610f049a 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -486,7 +486,52 @@ static struct smp_hotplug_thread watchdog_threads = {
         .unpark                 = watchdog_enable,
 };
 
-static int watchdog_enable_all_cpus(void)
+static void restart_watchdog_hrtimer(void *info)
+{
+        struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+        int ret;
+
+        /*
+         * No need to cancel and restart hrtimer if it is currently executing
+         * because it will reprogram itself with the new period now.
+         * We should never see it unqueued here because we are running per-cpu
+         * with interrupts disabled.
+         */
+        ret = hrtimer_try_to_cancel(hrtimer);
+        if (ret == 1)
+                hrtimer_start(hrtimer, ns_to_ktime(sample_period),
+                                HRTIMER_MODE_REL_PINNED);
+}
+
+static void update_timers(int cpu)
+{
+        struct call_single_data data = {.func = restart_watchdog_hrtimer};
+        /*
+         * Make sure that perf event counter will adopt to a new
+         * sampling period. Updating the sampling period directly would
+         * be much nicer but we do not have an API for that now so
+         * let's use a big hammer.
+         * Hrtimer will adopt the new period on the next tick but this
+         * might be late already so we have to restart the timer as well.
+         */
+        watchdog_nmi_disable(cpu);
+        __smp_call_function_single(cpu, &data, 1);
+        watchdog_nmi_enable(cpu);
+}
+
+static void update_timers_all_cpus(void)
+{
+        int cpu;
+
+        get_online_cpus();
+        preempt_disable();
+        for_each_online_cpu(cpu)
+                update_timers(cpu);
+        preempt_enable();
+        put_online_cpus();
+}
+
+static int watchdog_enable_all_cpus(bool sample_period_changed)
 {
         int err = 0;
 
@@ -496,6 +541,8 @@ static int watchdog_enable_all_cpus(void)
                         pr_err("Failed to create watchdog threads, disabled\n");
                 else
                         watchdog_running = 1;
+        } else if (sample_period_changed) {
+                update_timers_all_cpus();
         }
 
         return err;
@@ -520,13 +567,15 @@ int proc_dowatchdog(struct ctl_table *table, int write,
                     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         int err, old_thresh, old_enabled;
+        static DEFINE_MUTEX(watchdog_proc_mutex);
 
+        mutex_lock(&watchdog_proc_mutex);
         old_thresh = ACCESS_ONCE(watchdog_thresh);
         old_enabled = ACCESS_ONCE(watchdog_user_enabled);
 
         err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
         if (err || !write)
-                return err;
+                goto out;
 
         set_sample_period();
         /*
@@ -535,7 +584,7 @@ int proc_dowatchdog(struct ctl_table *table, int write,
          * watchdog_*_all_cpus() function takes care of this.
          */
         if (watchdog_user_enabled && watchdog_thresh)
-                err = watchdog_enable_all_cpus();
+                err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh);
         else
                 watchdog_disable_all_cpus();
 
@@ -544,7 +593,8 @@ int proc_dowatchdog(struct ctl_table *table, int write,
                 watchdog_thresh = old_thresh;
                 watchdog_user_enabled = old_enabled;
         }
-
+out:
+        mutex_unlock(&watchdog_proc_mutex);
         return err;
 }
 #endif /* CONFIG_SYSCTL */
@@ -554,5 +604,5 @@ void __init lockup_detector_init(void)
         set_sample_period();
 
         if (watchdog_user_enabled)
-                watchdog_enable_all_cpus();
+                watchdog_enable_all_cpus(false);
 }