4 files changed, 83 insertions, 37 deletions

diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 70f27e89012b..2b62fe86f9ec 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -105,7 +105,6 @@ config NO_HZ_FULL
         select RCU_USER_QS
         select RCU_NOCB_CPU
         select VIRT_CPU_ACCOUNTING_GEN
-        select CONTEXT_TRACKING_FORCE
         select IRQ_WORK
         help
          Adaptively try to shutdown the tick whenever possible, even when
@@ -134,6 +133,56 @@ config NO_HZ_FULL_ALL
          Note the boot CPU will still be kept outside the range to
          handle the timekeeping duty.
 
+config NO_HZ_FULL_SYSIDLE
+        bool "Detect full-system idle state for full dynticks system"
+        depends on NO_HZ_FULL
+        default n
+        help
+         At least one CPU must keep the scheduling-clock tick running for
+         timekeeping purposes whenever there is a non-idle CPU, where
+         "non-idle" also includes dynticks CPUs as long as they are
+         running non-idle tasks.  Because the underlying adaptive-tick
+         support cannot distinguish between all CPUs being idle and
+         all CPUs each running a single task in dynticks mode, the
+         underlying support simply ensures that there is always a CPU
+         handling the scheduling-clock tick, whether or not all CPUs
+         are idle.  This Kconfig option enables scalable detection of
+         the all-CPUs-idle state, thus allowing the scheduling-clock
+         tick to be disabled when all CPUs are idle.  Note that scalable
+         detection of the all-CPUs-idle state means that larger systems
+         will be slower to declare the all-CPUs-idle state.
+
+         Say Y if you would like to help debug all-CPUs-idle detection.
+
+         Say N if you are unsure.
+
+config NO_HZ_FULL_SYSIDLE_SMALL
+        int "Number of CPUs above which large-system approach is used"
+        depends on NO_HZ_FULL_SYSIDLE
+        range 1 NR_CPUS
+        default 8
+        help
+         The full-system idle detection mechanism takes a lazy approach
+         on large systems, as is required to attain decent scalability.
+         However, on smaller systems, scalability is not anywhere near as
+         large a concern as is energy efficiency.  The sysidle subsystem
+         therefore uses a fast but non-scalable algorithm for small
+         systems and a lazier but scalable algorithm for large systems.
+         This Kconfig parameter defines the number of CPUs in the largest
+         system that will be considered to be "small".
+
+         The default value will be fine in most cases.  Battery-powered
+         systems that (1) enable NO_HZ_FULL_SYSIDLE, (2) have larger
+         numbers of CPUs, and (3) are suffering from battery-lifetime
+         problems due to long sysidle latencies might wish to experiment
+         with larger values for this Kconfig parameter.  On the other
+         hand, they might be even better served by disabling NO_HZ_FULL
+         entirely, given that NO_HZ_FULL is intended for HPC and
+         real-time workloads that at present do not tend to be run on
+         battery-powered systems.
+
+         Take the default if you are unsure.
+
 config NO_HZ
         bool "Old Idle dynticks config"
         depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 8f5b3b98577b..bb2215174f05 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -516,13 +516,13 @@ static void sync_cmos_clock(struct work_struct *work)
         schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
 }
 
-static void notify_cmos_timer(void)
+void ntp_notify_cmos_timer(void)
 {
         schedule_delayed_work(&sync_cmos_work, 0);
 }
 
 #else
-static inline void notify_cmos_timer(void) { }
+void ntp_notify_cmos_timer(void) { }
 #endif
 
 
@@ -687,8 +687,6 @@ int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai)
         if (!(time_status & STA_NANO))
                 txc->time.tv_usec /= NSEC_PER_USEC;
 
-        notify_cmos_timer();
-
         return result;
 }
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index e8a1516cc0a3..3612fc77f834 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -23,6 +23,7 @@
 #include <linux/irq_work.h>
 #include <linux/posix-timers.h>
 #include <linux/perf_event.h>
+#include <linux/context_tracking.h>
 
 #include <asm/irq_regs.h>
 
@@ -148,8 +149,8 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 }
 
 #ifdef CONFIG_NO_HZ_FULL
-static cpumask_var_t nohz_full_mask;
-bool have_nohz_full_mask;
+cpumask_var_t tick_nohz_full_mask;
+bool tick_nohz_full_running;
 
 static bool can_stop_full_tick(void)
 {
@@ -182,7 +183,7 @@ static bool can_stop_full_tick(void)
                  * Don't allow the user to think they can get
                  * full NO_HZ with this machine.
                  */
-                WARN_ONCE(have_nohz_full_mask,
+                WARN_ONCE(tick_nohz_full_running,
                           "NO_HZ FULL will not work with unstable sched clock");
                 return false;
         }
@@ -197,7 +198,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now);
  * Re-evaluate the need for the tick on the current CPU
  * and restart it if necessary.
  */
-void tick_nohz_full_check(void)
+void __tick_nohz_full_check(void)
 {
         struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 
@@ -211,7 +212,7 @@ void tick_nohz_full_check(void)
 
 static void nohz_full_kick_work_func(struct irq_work *work)
 {
-        tick_nohz_full_check();
+        __tick_nohz_full_check();
 }
 
 static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
@@ -230,7 +231,7 @@ void tick_nohz_full_kick(void)
 
 static void nohz_full_kick_ipi(void *info)
 {
-        tick_nohz_full_check();
+        __tick_nohz_full_check();
 }
 
 /*
@@ -239,12 +240,13 @@ static void nohz_full_kick_ipi(void *info)
  */
 void tick_nohz_full_kick_all(void)
 {
-        if (!have_nohz_full_mask)
+        if (!tick_nohz_full_running)
                 return;
 
         preempt_disable();
-        smp_call_function_many(nohz_full_mask,
+        smp_call_function_many(tick_nohz_full_mask,
                                nohz_full_kick_ipi, NULL, false);
+        tick_nohz_full_kick();
         preempt_enable();
 }
 
@@ -253,7 +255,7 @@ void tick_nohz_full_kick_all(void)
  * It might need the tick due to per task/process properties:
  * perf events, posix cpu timers, ...
  */
-void tick_nohz_task_switch(struct task_struct *tsk)
+void __tick_nohz_task_switch(struct task_struct *tsk)
 {
         unsigned long flags;
 
@@ -269,31 +271,23 @@ out:
         local_irq_restore(flags);
 }
 
-int tick_nohz_full_cpu(int cpu)
-{
-        if (!have_nohz_full_mask)
-                return 0;
-
-        return cpumask_test_cpu(cpu, nohz_full_mask);
-}
-
 /* Parse the boot-time nohz CPU list from the kernel parameters. */
 static int __init tick_nohz_full_setup(char *str)
 {
         int cpu;
 
-        alloc_bootmem_cpumask_var(&nohz_full_mask);
-        if (cpulist_parse(str, nohz_full_mask) < 0) {
+        alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
+        if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
                 pr_warning("NOHZ: Incorrect nohz_full cpumask\n");
                 return 1;
         }
 
         cpu = smp_processor_id();
-        if (cpumask_test_cpu(cpu, nohz_full_mask)) {
+        if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
                 pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
-                cpumask_clear_cpu(cpu, nohz_full_mask);
+                cpumask_clear_cpu(cpu, tick_nohz_full_mask);
         }
-        have_nohz_full_mask = true;
+        tick_nohz_full_running = true;
 
         return 1;
 }
@@ -311,7 +305,7 @@ static int tick_nohz_cpu_down_callback(struct notifier_block *nfb,
                  * If we handle the timekeeping duty for full dynticks CPUs,
                  * we can't safely shutdown that CPU.
                  */
-                if (have_nohz_full_mask && tick_do_timer_cpu == cpu)
+                if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
                         return NOTIFY_BAD;
                 break;
         }
@@ -330,31 +324,34 @@ static int tick_nohz_init_all(void)
         int err = -1;
 
 #ifdef CONFIG_NO_HZ_FULL_ALL
-        if (!alloc_cpumask_var(&nohz_full_mask, GFP_KERNEL)) {
+        if (!alloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL)) {
                 pr_err("NO_HZ: Can't allocate full dynticks cpumask\n");
                 return err;
         }
         err = 0;
-        cpumask_setall(nohz_full_mask);
-        cpumask_clear_cpu(smp_processor_id(), nohz_full_mask);
-        have_nohz_full_mask = true;
+        cpumask_setall(tick_nohz_full_mask);
+        cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask);
+        tick_nohz_full_running = true;
 #endif
         return err;
 }
 
 void __init tick_nohz_init(void)
 {
-        if (!have_nohz_full_mask) {
+        int cpu;
+
+        if (!tick_nohz_full_running) {
                 if (tick_nohz_init_all() < 0)
                         return;
         }
 
+        for_each_cpu(cpu, tick_nohz_full_mask)
+                context_tracking_cpu_set(cpu);
+
         cpu_notifier(tick_nohz_cpu_down_callback, 0);
-        cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), nohz_full_mask);
+        cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), tick_nohz_full_mask);
         pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf);
 }
-#else
-#define have_nohz_full_mask (0)
 #endif
 
 /*
@@ -732,7 +729,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
                 return false;
         }
 
-        if (have_nohz_full_mask) {
+        if (tick_nohz_full_enabled()) {
                 /*
                  * Keep the tick alive to guarantee timekeeping progression
                  * if there are full dynticks CPUs around
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 48b9fffabdc2..947ba25a95a0 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1703,6 +1703,8 @@ int do_adjtimex(struct timex *txc)
         write_seqcount_end(&timekeeper_seq);
         raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
+        ntp_notify_cmos_timer();
+
         return ret;
 }