20 files changed, 124 insertions, 57 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 0125589c7428..48851327a15e 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2669,7 +2669,7 @@ static bool css_visible(struct cgroup_subsys_state *css)
  *
  * Returns 0 on success, -errno on failure.  On failure, csses which have
  * been processed already aren't cleaned up.  The caller is responsible for
- * cleaning up with cgroup_apply_control_disble().
+ * cleaning up with cgroup_apply_control_disable().
  */
 static int cgroup_apply_control_enable(struct cgroup *cgrp)
 {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6f41548f2e32..a17ed56c8ce1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -998,7 +998,7 @@ list_update_cgroup_event(struct perf_event *event,
  */
 #define PERF_CPU_HRTIMER (1000 / HZ)
 /*
- * function must be called with interrupts disbled
+ * function must be called with interrupts disabled
  */
 static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
 {
diff --git a/kernel/exit.c b/kernel/exit.c
index e126ebf2400c..516acdb0e0ec 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -554,7 +554,6 @@ static void exit_mm(void)
         enter_lazy_tlb(mm, current);
         task_unlock(current);
         mm_update_next_owner(mm);
-        userfaultfd_exit(mm);
         mmput(mm);
         if (test_thread_flag(TIF_MEMDIE))
                 exit_oom_victim();
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b56a558e406d..b118735fea9d 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -614,13 +614,13 @@ static int kexec_calculate_store_digests(struct kimage *image)
                 ret = crypto_shash_final(desc, digest);
                 if (ret)
                         goto out_free_digest;
-                ret = kexec_purgatory_get_set_symbol(image, "sha_regions",
-                                                sha_regions, sha_region_sz, 0);
+                ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions",
+                                                     sha_regions, sha_region_sz, 0);
                 if (ret)
                         goto out_free_digest;
 
-                ret = kexec_purgatory_get_set_symbol(image, "sha256_digest",
-                                                digest, SHA256_DIGEST_SIZE, 0);
+                ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest",
+                                                     digest, SHA256_DIGEST_SIZE, 0);
                 if (ret)
                         goto out_free_digest;
         }
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 4cef7e4706b0..799a8a452187 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -15,11 +15,7 @@ int kimage_is_destination_range(struct kimage *image,
 extern struct mutex kexec_mutex;
 
 #ifdef CONFIG_KEXEC_FILE
-struct kexec_sha_region {
-        unsigned long start;
-        unsigned long len;
-};
-
+#include <linux/purgatory.h>
 void kimage_file_post_load_cleanup(struct kimage *image);
 #else /* CONFIG_KEXEC_FILE */
 static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 12e38c213b70..a95e5d1f4a9c 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3262,10 +3262,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
         if (depth) {
                 hlock = curr->held_locks + depth - 1;
                 if (hlock->class_idx == class_idx && nest_lock) {
-                        if (hlock->references)
+                        if (hlock->references) {
+                                /*
+                                 * Check: unsigned int references:12, overflow.
+                                 */
+                                if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1))
+                                        return 0;
+
                                 hlock->references++;
-                        else
+                        } else {
                                 hlock->references = 2;
+                        }
 
                         return 1;
                 }
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index da6c9a34f62f..6b7abb334ca6 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -50,7 +50,7 @@ static void test_mutex_work(struct work_struct *work)
 
         if (mtx->flags & TEST_MTX_TRY) {
                 while (!ww_mutex_trylock(&mtx->mutex))
-                        cpu_relax();
+                        cond_resched();
         } else {
                 ww_mutex_lock(&mtx->mutex, NULL);
         }
@@ -88,7 +88,7 @@ static int __test_mutex(unsigned int flags)
                                 ret = -EINVAL;
                                 break;
                         }
-                        cpu_relax();
+                        cond_resched();
                 } while (time_before(jiffies, timeout));
         } else {
                 ret = wait_for_completion_timeout(&mtx.done, TIMEOUT);
@@ -627,7 +627,7 @@ static int __init test_ww_mutex_init(void)
         if (ret)
                 return ret;
 
-        ret = stress(4096, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
+        ret = stress(4095, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
         if (ret)
                 return ret;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 956383844116..3b31fc05a0f1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3287,10 +3287,15 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
         struct task_struct *p;
 
         /*
-         * Optimization: we know that if all tasks are in
-         * the fair class we can call that function directly:
+         * Optimization: we know that if all tasks are in the fair class we can
+         * call that function directly, but only if the @prev task wasn't of a
+         * higher scheduling class, because otherwise those loose the
+         * opportunity to pull in more work from other CPUs.
          */
-        if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
+        if (likely((prev->sched_class == &idle_sched_class ||
+                    prev->sched_class == &fair_sched_class) &&
+                   rq->nr_running == rq->cfs.h_nr_running)) {
+
                 p = fair_sched_class.pick_next_task(rq, prev, rf);
                 if (unlikely(p == RETRY_TASK))
                         goto again;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 8f8de3d4d6b7..cd7cd489f739 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -36,6 +36,7 @@ struct sugov_policy {
         u64 last_freq_update_time;
         s64 freq_update_delay_ns;
         unsigned int next_freq;
+        unsigned int cached_raw_freq;
 
         /* The next fields are only needed if fast switch cannot be used. */
         struct irq_work irq_work;
@@ -52,7 +53,6 @@ struct sugov_cpu {
         struct update_util_data update_util;
         struct sugov_policy *sg_policy;
 
-        unsigned int cached_raw_freq;
         unsigned long iowait_boost;
         unsigned long iowait_boost_max;
         u64 last_update;
@@ -116,7 +116,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
 
 /**
  * get_next_freq - Compute a new frequency for a given cpufreq policy.
- * @sg_cpu: schedutil cpu object to compute the new frequency for.
+ * @sg_policy: schedutil policy object to compute the new frequency for.
  * @util: Current CPU utilization.
  * @max: CPU capacity.
  *
@@ -136,19 +136,18 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
  * next_freq (as calculated above) is returned, subject to policy min/max and
  * cpufreq driver limitations.
  */
-static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
-                                  unsigned long max)
+static unsigned int get_next_freq(struct sugov_policy *sg_policy,
+                                  unsigned long util, unsigned long max)
 {
-        struct sugov_policy *sg_policy = sg_cpu->sg_policy;
         struct cpufreq_policy *policy = sg_policy->policy;
         unsigned int freq = arch_scale_freq_invariant() ?
                                 policy->cpuinfo.max_freq : policy->cur;
 
         freq = (freq + (freq >> 2)) * util / max;
 
-        if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+        if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
                 return sg_policy->next_freq;
-        sg_cpu->cached_raw_freq = freq;
+        sg_policy->cached_raw_freq = freq;
         return cpufreq_driver_resolve_freq(policy, freq);
 }
 
@@ -213,7 +212,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
         } else {
                 sugov_get_util(&util, &max);
                 sugov_iowait_boost(sg_cpu, &util, &max);
-                next_f = get_next_freq(sg_cpu, util, max);
+                next_f = get_next_freq(sg_policy, util, max);
         }
         sugov_update_commit(sg_policy, time, next_f);
 }
@@ -267,7 +266,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
                 sugov_iowait_boost(j_sg_cpu, &util, &max);
         }
 
-        return get_next_freq(sg_cpu, util, max);
+        return get_next_freq(sg_policy, util, max);
 }
 
 static void sugov_update_shared(struct update_util_data *hook, u64 time,
@@ -580,6 +579,7 @@ static int sugov_start(struct cpufreq_policy *policy)
         sg_policy->next_freq = UINT_MAX;
         sg_policy->work_in_progress = false;
         sg_policy->need_freq_update = false;
+        sg_policy->cached_raw_freq = 0;
 
         for_each_cpu(cpu, policy->cpus) {
                 struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
@@ -590,7 +590,6 @@ static int sugov_start(struct cpufreq_policy *policy)
                         sg_cpu->max = 0;
                         sg_cpu->flags = SCHED_CPUFREQ_RT;
                         sg_cpu->last_update = 0;
-                        sg_cpu->cached_raw_freq = 0;
                         sg_cpu->iowait_boost = 0;
                         sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
                         cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3e88b35ac157..dea138964b91 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5799,7 +5799,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
          * Due to large variance we need a large fuzz factor; hackbench in
          * particularly is sensitive here.
          */
-        if ((avg_idle / 512) < avg_cost)
+        if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost)
                 return -1;
 
         time = local_clock();
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 69631fa46c2f..1b3c8189b286 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -51,6 +51,11 @@ SCHED_FEAT(NONTASK_CAPACITY, true)
  */
 SCHED_FEAT(TTWU_QUEUE, true)
 
+/*
+ * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
+ */
+SCHED_FEAT(SIS_AVG_CPU, false)
+
 #ifdef HAVE_RT_PUSH_IPI
 /*
  * In order to avoid a thundering herd attack of CPUs that are
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 4d2ea6f25568..b8c84c6dee64 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -242,6 +242,45 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
 }
 EXPORT_SYMBOL(prepare_to_wait_event);
 
+/*
+ * Note! These two wait functions are entered with the
+ * wait-queue lock held (and interrupts off in the _irq
+ * case), so there is no race with testing the wakeup
+ * condition in the caller before they add the wait
+ * entry to the wake queue.
+ */
+int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait)
+{
+        if (likely(list_empty(&wait->task_list)))
+                __add_wait_queue_tail(wq, wait);
+
+        set_current_state(TASK_INTERRUPTIBLE);
+        if (signal_pending(current))
+                return -ERESTARTSYS;
+
+        spin_unlock(&wq->lock);
+        schedule();
+        spin_lock(&wq->lock);
+        return 0;
+}
+EXPORT_SYMBOL(do_wait_intr);
+
+int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait)
+{
+        if (likely(list_empty(&wait->task_list)))
+                __add_wait_queue_tail(wq, wait);
+
+        set_current_state(TASK_INTERRUPTIBLE);
+        if (signal_pending(current))
+                return -ERESTARTSYS;
+
+        spin_unlock_irq(&wq->lock);
+        schedule();
+        spin_lock_irq(&wq->lock);
+        return 0;
+}
+EXPORT_SYMBOL(do_wait_intr_irq);
+
 /**
  * finish_wait - clean up after waiting in a queue
  * @q: waitqueue waited on
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7906b3f0c41a..497719127bf9 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -125,7 +125,7 @@ int register_refined_jiffies(long cycles_per_second)
         shift_hz += cycles_per_tick/2;
         do_div(shift_hz, cycles_per_tick);
         /* Calculate nsec_per_tick using shift_hz */
-        nsec_per_tick = (u64)TICK_NSEC << 8;
+        nsec_per_tick = (u64)NSEC_PER_SEC << 8;
         nsec_per_tick += (u32)shift_hz/2;
         do_div(nsec_per_tick, (u32)shift_hz);
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d5038005eb5d..d4a06e714645 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -429,7 +429,7 @@ config BLK_DEV_IO_TRACE
 
           If unsure, say N.
 
-config KPROBE_EVENT
+config KPROBE_EVENTS
         depends on KPROBES
         depends on HAVE_REGS_AND_STACK_ACCESS_API
         bool "Enable kprobes-based dynamic events"
@@ -447,7 +447,7 @@ config KPROBE_EVENT
           This option is also required by perf-probe subcommand of perf tools.
           If you want to use perf tools, this option is strongly recommended.
 
-config UPROBE_EVENT
+config UPROBE_EVENTS
         bool "Enable uprobes-based dynamic events"
         depends on ARCH_SUPPORTS_UPROBES
         depends on MMU
@@ -466,7 +466,7 @@ config UPROBE_EVENT
 
 config BPF_EVENTS
         depends on BPF_SYSCALL
-        depends on (KPROBE_EVENT || UPROBE_EVENT) && PERF_EVENTS
+        depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS
         bool
         default y
         help
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index e57980845549..90f2701d92a7 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -57,7 +57,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
 obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
-obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
 ifeq ($(CONFIG_PM),y)
 obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
@@ -66,7 +66,7 @@ ifeq ($(CONFIG_TRACING),y)
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
-obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
+obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
 
 obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0d1597c9ee30..b9691ee8f6c1 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4416,16 +4416,24 @@ static int __init set_graph_notrace_function(char *str)
 }
 __setup("ftrace_graph_notrace=", set_graph_notrace_function);
 
+static int __init set_graph_max_depth_function(char *str)
+{
+        if (!str)
+                return 0;
+        fgraph_max_depth = simple_strtoul(str, NULL, 0);
+        return 1;
+}
+__setup("ftrace_graph_max_depth=", set_graph_max_depth_function);
+
 static void __init set_ftrace_early_graph(char *buf, int enable)
 {
         int ret;
         char *func;
         struct ftrace_hash *hash;
 
-        if (enable)
-                hash = ftrace_graph_hash;
-        else
-                hash = ftrace_graph_notrace_hash;
+        hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
+        if (WARN_ON(!hash))
+                return;
 
         while (buf) {
                 func = strsep(&buf, ",");
@@ -4435,6 +4443,11 @@ static void __init set_ftrace_early_graph(char *buf, int enable)
                         printk(KERN_DEBUG "ftrace: function %s not "
                                           "traceable\n", func);
         }
+
+        if (enable)
+                ftrace_graph_hash = hash;
+        else
+                ftrace_graph_notrace_hash = hash;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -5488,7 +5501,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
  * Normally the mcount trampoline will call the ops->func, but there
  * are times that it should not. For example, if the ops does not
  * have its own recursion protection, then it should call the
- * ftrace_ops_recurs_func() instead.
+ * ftrace_ops_assist_func() instead.
  *
  * Returns the function that the trampoline should call for @ops.
  */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 707445ceb7ef..f35109514a01 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4341,22 +4341,22 @@ static const char readme_msg[] =
         "\t\t\t  traces\n"
 #endif
 #endif /* CONFIG_STACK_TRACER */
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
         "  kprobe_events\t\t- Add/remove/show the kernel dynamic events\n"
         "\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
         "  uprobe_events\t\t- Add/remove/show the userspace dynamic events\n"
         "\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#if defined(CONFIG_KPROBE_EVENT) || defined(CONFIG_UPROBE_EVENT)
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
         "\t  accepts: event-definitions (one definition per line)\n"
         "\t   Format: p|r[:[<group>/]<event>] <place> [<args>]\n"
         "\t           -:[<group>/]<event>\n"
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
         "\t    place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
         "\t    place: <path>:<offset>\n"
 #endif
         "\t     args: <name>=fetcharg[:type]\n"
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 0c0ae54d44c6..903273c93e61 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -248,7 +248,7 @@ ASSIGN_FETCH_FUNC(file_offset, ftype),			\
 #define FETCH_TYPE_STRING       0
 #define FETCH_TYPE_STRSIZE      1
 
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 struct symbol_cache;
 unsigned long update_symbol_cache(struct symbol_cache *sc);
 void free_symbol_cache(struct symbol_cache *sc);
@@ -278,7 +278,7 @@ alloc_symbol_cache(const char *sym, long offset)
 {
         return NULL;
 }
-#endif /* CONFIG_KPROBE_EVENT */
+#endif /* CONFIG_KPROBE_EVENTS */
 
 struct probe_arg {
         struct fetch_param      fetch;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 1d68b5b7ad41..5fb1f2c87e6b 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -65,7 +65,7 @@ void stack_trace_print(void)
 }
 
 /*
- * When arch-specific code overides this function, the following
+ * When arch-specific code overrides this function, the following
  * data should be filled up, assuming stack_trace_max_lock is held to
  * prevent concurrent updates.
  *     stack_trace_index[]
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 62630a40ab3a..b4eeee03934f 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -144,7 +144,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 
                 new->ns = ns;
                 new->uid = uid;
-                atomic_set(&new->count, 0);
+                new->count = 0;
 
                 spin_lock_irq(&ucounts_lock);
                 ucounts = find_ucounts(ns, uid, hashent);
@@ -155,8 +155,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
                         ucounts = new;
                 }
         }
-        if (!atomic_add_unless(&ucounts->count, 1, INT_MAX))
+        if (ucounts->count == INT_MAX)
                 ucounts = NULL;
+        else
+                ucounts->count += 1;
         spin_unlock_irq(&ucounts_lock);
         return ucounts;
 }
@@ -165,13 +167,15 @@ static void put_ucounts(struct ucounts *ucounts)
 {
         unsigned long flags;
 
-        if (atomic_dec_and_test(&ucounts->count)) {
-                spin_lock_irqsave(&ucounts_lock, flags);
+        spin_lock_irqsave(&ucounts_lock, flags);
+        ucounts->count -= 1;
+        if (!ucounts->count)
                 hlist_del_init(&ucounts->node);
-                spin_unlock_irqrestore(&ucounts_lock, flags);
+        else
+                ucounts = NULL;
+        spin_unlock_irqrestore(&ucounts_lock, flags);
 
-                kfree(ucounts);
-        }
+        kfree(ucounts);
 }
 
 static inline bool atomic_inc_below(atomic_t *v, int u)