summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--Documentation/RCU/trace.txt4
-rw-r--r--include/linux/hardirq.h21
-rw-r--r--include/linux/rcupdate.h21
-rw-r--r--include/linux/tick.h11
-rw-r--r--include/trace/events/rcu.h10
-rw-r--r--kernel/rcutiny.c124
-rw-r--r--kernel/rcutree.c229
-rw-r--r--kernel/rcutree.h15
-rw-r--r--kernel/rcutree_trace.c10
-rw-r--r--kernel/time/tick-sched.c6
10 files changed, 297 insertions, 154 deletions
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index aaf65f6..49587ab 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -105,14 +105,10 @@ o "dt" is the current value of the dyntick counter that is incremented
or one greater than the interrupt-nesting depth otherwise.
The number after the second "/" is the NMI nesting depth.
- This field is displayed only for CONFIG_NO_HZ kernels.
-
o "df" is the number of times that some other CPU has forced a
quiescent state on behalf of this CPU due to this CPU being in
dynticks-idle state.
- This field is displayed only for CONFIG_NO_HZ kernels.
-
o "of" is the number of times that some other CPU has forced a
quiescent state on behalf of this CPU due to this CPU being
offline. In a perfect world, this might never happen, but it
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index f743883..bb7f309 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -139,20 +139,7 @@ static inline void account_system_vtime(struct task_struct *tsk)
extern void account_system_vtime(struct task_struct *tsk);
#endif
-#if defined(CONFIG_NO_HZ)
#if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
-extern void rcu_enter_nohz(void);
-extern void rcu_exit_nohz(void);
-
-static inline void rcu_irq_enter(void)
-{
- rcu_exit_nohz();
-}
-
-static inline void rcu_irq_exit(void)
-{
- rcu_enter_nohz();
-}
static inline void rcu_nmi_enter(void)
{
@@ -163,17 +150,9 @@ static inline void rcu_nmi_exit(void)
}
#else
-extern void rcu_irq_enter(void);
-extern void rcu_irq_exit(void);
extern void rcu_nmi_enter(void);
extern void rcu_nmi_exit(void);
#endif
-#else
-# define rcu_irq_enter() do { } while (0)
-# define rcu_irq_exit() do { } while (0)
-# define rcu_nmi_enter() do { } while (0)
-# define rcu_nmi_exit() do { } while (0)
-#endif /* #if defined(CONFIG_NO_HZ) */
/*
* It is safe to do non-atomic ops on ->hardirq_context,
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 2cf4226..cd1ad4b 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -177,23 +177,10 @@ extern void rcu_sched_qs(int cpu);
extern void rcu_bh_qs(int cpu);
extern void rcu_check_callbacks(int cpu, int user);
struct notifier_block;
-
-#ifdef CONFIG_NO_HZ
-
-extern void rcu_enter_nohz(void);
-extern void rcu_exit_nohz(void);
-
-#else /* #ifdef CONFIG_NO_HZ */
-
-static inline void rcu_enter_nohz(void)
-{
-}
-
-static inline void rcu_exit_nohz(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_NO_HZ */
+extern void rcu_idle_enter(void);
+extern void rcu_idle_exit(void);
+extern void rcu_irq_enter(void);
+extern void rcu_irq_exit(void);
/*
* Infrastructure to implement the synchronize_() primitives in
diff --git a/include/linux/tick.h b/include/linux/tick.h
index b232ccc..ca40838 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -127,8 +127,15 @@ extern ktime_t tick_nohz_get_sleep_length(void);
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
# else
-static inline void tick_nohz_stop_sched_tick(int inidle) { }
-static inline void tick_nohz_restart_sched_tick(void) { }
+static inline void tick_nohz_stop_sched_tick(int inidle)
+{
+ if (inidle)
+ rcu_idle_enter();
+}
+static inline void tick_nohz_restart_sched_tick(void)
+{
+ rcu_idle_exit();
+}
static inline ktime_t tick_nohz_get_sleep_length(void)
{
ktime_t len = { .tv64 = NSEC_PER_SEC/HZ };
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 669fbd6..e577180 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -246,19 +246,21 @@ TRACE_EVENT(rcu_fqs,
*/
TRACE_EVENT(rcu_dyntick,
- TP_PROTO(char *polarity),
+ TP_PROTO(char *polarity, int nesting),
- TP_ARGS(polarity),
+ TP_ARGS(polarity, nesting),
TP_STRUCT__entry(
__field(char *, polarity)
+ __field(int, nesting)
),
TP_fast_assign(
__entry->polarity = polarity;
+ __entry->nesting = nesting;
),
- TP_printk("%s", __entry->polarity)
+ TP_printk("%s %d", __entry->polarity, __entry->nesting)
);
/*
@@ -443,7 +445,7 @@ TRACE_EVENT(rcu_batch_end,
#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks) do { } while (0)
#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
-#define trace_rcu_dyntick(polarity) do { } while (0)
+#define trace_rcu_dyntick(polarity, nesting) do { } while (0)
#define trace_rcu_callback(rcuname, rhp, qlen) do { } while (0)
#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen) do { } while (0)
#define trace_rcu_batch_start(rcuname, qlen, blimit) do { } while (0)
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 636af6d..3ab77bd 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -53,31 +53,122 @@ static void __call_rcu(struct rcu_head *head,
#include "rcutiny_plugin.h"
-#ifdef CONFIG_NO_HZ
+static long long rcu_dynticks_nesting = LLONG_MAX / 2;
-static long rcu_dynticks_nesting = 1;
+/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */
+static void rcu_idle_enter_common(void)
+{
+ if (rcu_dynticks_nesting) {
+ RCU_TRACE(trace_rcu_dyntick("--=", rcu_dynticks_nesting));
+ return;
+ }
+ RCU_TRACE(trace_rcu_dyntick("Start", rcu_dynticks_nesting));
+ if (!idle_cpu(smp_processor_id())) {
+ WARN_ON_ONCE(1); /* must be idle task! */
+ RCU_TRACE(trace_rcu_dyntick("Error on entry: not idle task",
+ rcu_dynticks_nesting));
+ ftrace_dump(DUMP_ALL);
+ }
+ rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+}
/*
- * Enter dynticks-idle mode, which is an extended quiescent state
- * if we have fully entered that mode (i.e., if the new value of
- * dynticks_nesting is zero).
+ * Enter idle, which is an extended quiescent state if we have fully
+ * entered that mode (i.e., if the new value of dynticks_nesting is zero).
*/
-void rcu_enter_nohz(void)
+void rcu_idle_enter(void)
{
- if (--rcu_dynticks_nesting == 0)
- rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+ unsigned long flags;
+
+ local_irq_save(flags);
+ rcu_dynticks_nesting = 0;
+ rcu_idle_enter_common();
+ local_irq_restore(flags);
}
/*
- * Exit dynticks-idle mode, so that we are no longer in an extended
- * quiescent state.
+ * Exit an interrupt handler towards idle.
+ */
+void rcu_irq_exit(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ rcu_dynticks_nesting--;
+ WARN_ON_ONCE(rcu_dynticks_nesting < 0);
+ rcu_idle_enter_common();
+ local_irq_restore(flags);
+}
+
+/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcutree.c. */
+static void rcu_idle_exit_common(long long oldval)
+{
+ if (oldval) {
+ RCU_TRACE(trace_rcu_dyntick("++=", rcu_dynticks_nesting));
+ return;
+ }
+ RCU_TRACE(trace_rcu_dyntick("End", oldval));
+ if (!idle_cpu(smp_processor_id())) {
+ WARN_ON_ONCE(1); /* must be idle task! */
+ RCU_TRACE(trace_rcu_dyntick("Error on exit: not idle task",
+ oldval));
+ ftrace_dump(DUMP_ALL);
+ }
+}
+
+/*
+ * Exit idle, so that we are no longer in an extended quiescent state.
*/
-void rcu_exit_nohz(void)
+void rcu_idle_exit(void)
{
+ unsigned long flags;
+ long long oldval;
+
+ local_irq_save(flags);
+ oldval = rcu_dynticks_nesting;
+ WARN_ON_ONCE(oldval != 0);
+ rcu_dynticks_nesting = LLONG_MAX / 2;
+ rcu_idle_exit_common(oldval);
+ local_irq_restore(flags);
+}
+
+/*
+ * Enter an interrupt handler, moving away from idle.
+ */
+void rcu_irq_enter(void)
+{
+ unsigned long flags;
+ long long oldval;
+
+ local_irq_save(flags);
+ oldval = rcu_dynticks_nesting;
rcu_dynticks_nesting++;
+ WARN_ON_ONCE(rcu_dynticks_nesting == 0);
+ rcu_idle_exit_common(oldval);
+ local_irq_restore(flags);
+}
+
+#ifdef CONFIG_PROVE_RCU
+
+/*
+ * Test whether RCU thinks that the current CPU is idle.
+ */
+int rcu_is_cpu_idle(void)
+{
+ return !rcu_dynticks_nesting;
}
-#endif /* #ifdef CONFIG_NO_HZ */
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
+/*
+ * Test whether the current CPU was interrupted from idle. Nested
+ * interrupts don't count, we must be running at the first interrupt
+ * level.
+ */
+int rcu_is_cpu_rrupt_from_idle(void)
+{
+ return rcu_dynticks_nesting <= 0;
+}
/*
* Helper function for rcu_sched_qs() and rcu_bh_qs().
@@ -126,14 +217,13 @@ void rcu_bh_qs(int cpu)
/*
* Check to see if the scheduling-clock interrupt came from an extended
- * quiescent state, and, if so, tell RCU about it.
+ * quiescent state, and, if so, tell RCU about it. This function must
+ * be called from hardirq context. It is normally called from the
+ * scheduling-clock interrupt.
*/
void rcu_check_callbacks(int cpu, int user)
{
- if (user ||
- (idle_cpu(cpu) &&
- !in_softirq() &&
- hardirq_count() <= (1 << HARDIRQ_SHIFT)))
+ if (user || rcu_is_cpu_rrupt_from_idle())
rcu_sched_qs(cpu);
else if (!in_softirq())
rcu_bh_qs(cpu);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 5d0b55a..1c40326 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -195,12 +195,10 @@ void rcu_note_context_switch(int cpu)
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);
-#ifdef CONFIG_NO_HZ
DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
- .dynticks_nesting = 1,
+ .dynticks_nesting = LLONG_MAX / 2,
.dynticks = ATOMIC_INIT(1),
};
-#endif /* #ifdef CONFIG_NO_HZ */
static int blimit = 10; /* Maximum callbacks per rcu_do_batch. */
static int qhimark = 10000; /* If this many pending, ignore blimit. */
@@ -328,11 +326,11 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
return 1;
}
- /* If preemptible RCU, no point in sending reschedule IPI. */
- if (rdp->preemptible)
- return 0;
-
- /* The CPU is online, so send it a reschedule IPI. */
+ /*
+ * The CPU is online, so send it a reschedule IPI. This forces
+ * it through the scheduler, and (inefficiently) also handles cases
+ * where idle loops fail to inform RCU about the CPU being idle.
+ */
if (rdp->cpu != smp_processor_id())
smp_send_reschedule(rdp->cpu);
else
@@ -343,51 +341,97 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
#endif /* #ifdef CONFIG_SMP */
-#ifdef CONFIG_NO_HZ
+/*
+ * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle
+ *
+ * If the new value of the ->dynticks_nesting counter now is zero,
+ * we really have entered idle, and must do the appropriate accounting.
+ * The caller must have disabled interrupts.
+ */
+static void rcu_idle_enter_common(struct rcu_dynticks *rdtp)
+{
+ if (rdtp->dynticks_nesting) {
+ trace_rcu_dyntick("--=", rdtp->dynticks_nesting);
+ return;
+ }
+ trace_rcu_dyntick("Start", rdtp->dynticks_nesting);
+ if (!idle_cpu(smp_processor_id())) {
+ WARN_ON_ONCE(1); /* must be idle task! */
+ trace_rcu_dyntick("Error on entry: not idle task",
+ rdtp->dynticks_nesting);
+ ftrace_dump(DUMP_ALL);
+ }
+ /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+ smp_mb__before_atomic_inc(); /* See above. */
+ atomic_inc(&rdtp->dynticks);
+ smp_mb__after_atomic_inc(); /* Force ordering with next sojourn. */
+ WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+}
/**
- * rcu_enter_nohz - inform RCU that current CPU is entering nohz
+ * rcu_idle_enter - inform RCU that current CPU is entering idle
*
- * Enter nohz mode, in other words, -leave- the mode in which RCU
+ * Enter idle mode, in other words, -leave- the mode in which RCU
* read-side critical sections can occur. (Though RCU read-side
- * critical sections can occur in irq handlers in nohz mode, a possibility
- * handled by rcu_irq_enter() and rcu_irq_exit()).
+ * critical sections can occur in irq handlers in idle, a possibility
+ * handled by irq_enter() and irq_exit().)
+ *
+ * We crowbar the ->dynticks_nesting field to zero to allow for
+ * the possibility of usermode upcalls having messed up our count
+ * of interrupt nesting level during the prior busy period.
*/
-void rcu_enter_nohz(void)
+void rcu_idle_enter(void)
{
unsigned long flags;
struct rcu_dynticks *rdtp;
local_irq_save(flags);
rdtp = &__get_cpu_var(rcu_dynticks);
- if (--rdtp->dynticks_nesting) {
- local_irq_restore(flags);
- return;
- }
- trace_rcu_dyntick("Start");
- /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
- smp_mb__before_atomic_inc(); /* See above. */
- atomic_inc(&rdtp->dynticks);
- smp_mb__after_atomic_inc(); /* Force ordering with next sojourn. */
- WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+ rdtp->dynticks_nesting = 0;
+ rcu_idle_enter_common(rdtp);
local_irq_restore(flags);
}
-/*
- * rcu_exit_nohz - inform RCU that current CPU is leaving nohz
+/**
+ * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
+ *
+ * Exit from an interrupt handler, which might possibly result in entering
+ * idle mode, in other words, leaving the mode in which read-side critical
+ * sections can occur.
*
- * Exit nohz mode, in other words, -enter- the mode in which RCU
- * read-side critical sections normally occur.
+ * This code assumes that the idle loop never does anything that might
+ * result in unbalanced calls to irq_enter() and irq_exit(). If your
+ * architecture violates this assumption, RCU will give you what you
+ * deserve, good and hard. But very infrequently and irreproducibly.
+ *
+ * Use things like work queues to work around this limitation.
+ *
+ * You have been warned.
*/
-void rcu_exit_nohz(void)
+void rcu_irq_exit(void)
{
unsigned long flags;
struct rcu_dynticks *rdtp;
local_irq_save(flags);
rdtp = &__get_cpu_var(rcu_dynticks);
- if (rdtp->dynticks_nesting++) {
- local_irq_restore(flags);
+ rdtp->dynticks_nesting--;
+ WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
+ rcu_idle_enter_common(rdtp);
+ local_irq_restore(flags);
+}
+
+/*
+ * rcu_idle_exit_common - inform RCU that current CPU is moving away from idle
+ *
+ * If the new value of the ->dynticks_nesting counter was previously zero,
+ * we really have exited idle, and must do the appropriate accounting.
+ * The caller must have disabled interrupts.
+ */
+static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval)
+{
+ if (oldval) {
+ trace_rcu_dyntick("++=", rdtp->dynticks_nesting);
return;
}
smp_mb__before_atomic_inc(); /* Force ordering w/previous sojourn. */
@@ -395,7 +439,71 @@ void rcu_exit_nohz(void)
/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
smp_mb__after_atomic_inc(); /* See above. */
WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
- trace_rcu_dyntick("End");
+ trace_rcu_dyntick("End", oldval);
+ if (!idle_cpu(smp_processor_id())) {
+ WARN_ON_ONCE(1); /* must be idle task! */
+ trace_rcu_dyntick("Error on exit: not idle task", oldval);
+ ftrace_dump(DUMP_ALL);
+ }
+}
+
+/**
+ * rcu_idle_exit - inform RCU that current CPU is leaving idle
+ *
+ * Exit idle mode, in other words, -enter- the mode in which RCU
+ * read-side critical sections can occur.
+ *
+ * We crowbar the ->dynticks_nesting field to LLONG_MAX/2 to allow for
+ * the possibility of usermode upcalls messing up our count
+ * of interrupt nesting level during the busy period that is just
+ * now starting.
+ */
+void rcu_idle_exit(void)
+{
+ unsigned long flags;
+ struct rcu_dynticks *rdtp;
+ long long oldval;
+
+ local_irq_save(flags);
+ rdtp = &__get_cpu_var(rcu_dynticks);
+ oldval = rdtp->dynticks_nesting;
+ WARN_ON_ONCE(oldval != 0);
+ rdtp->dynticks_nesting = LLONG_MAX / 2;
+ rcu_idle_exit_common(rdtp, oldval);
+ local_irq_restore(flags);
+}
+
+/**
+ * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
+ *
+ * Enter an interrupt handler, which might possibly result in exiting
+ * idle mode, in other words, entering the mode in which read-side critical
+ * sections can occur.
+ *
+ * Note that the Linux kernel is fully capable of entering an interrupt
+ * handler that it never exits, for example when doing upcalls to
+ * user mode! This code assumes that the idle loop never does upcalls to
+ * user mode. If your architecture does do upcalls from the idle loop (or
+ * does anything else that results in unbalanced calls to the irq_enter()
+ * and irq_exit() functions), RCU will give you what you deserve, good
+ * and hard. But very infrequently and irreproducibly.
+ *
+ * Use things like work queues to work around this limitation.
+ *
+ * You have been warned.
+ */
+void rcu_irq_enter(void)
+{
+ unsigned long flags;
+ struct rcu_dynticks *rdtp;
+ long long oldval;
+
+ local_irq_save(flags);
+ rdtp = &__get_cpu_var(rcu_dynticks);
+ oldval = rdtp->dynticks_nesting;
+ rdtp->dynticks_nesting++;
+ WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
+ rcu_idle_exit_common(rdtp, oldval);
local_irq_restore(flags);
}
@@ -442,27 +550,32 @@ void rcu_nmi_exit(void)
WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
}
+#ifdef CONFIG_PROVE_RCU
+
/**
- * rcu_irq_enter - inform RCU of entry to hard irq context
+ * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle
*
- * If the CPU was idle with dynamic ticks active, this updates the
- * rdtp->dynticks to let the RCU handling know that the CPU is active.
+ * If the current CPU is in its idle loop and is neither in an interrupt
+ * or NMI handler, return true. The caller must have at least disabled
+ * preemption.
*/
-void rcu_irq_enter(void)
+int rcu_is_cpu_idle(void)
{
- rcu_exit_nohz();
+ return (atomic_read(&__get_cpu_var(rcu_dynticks).dynticks) & 0x1) == 0;
}
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
/**
- * rcu_irq_exit - inform RCU of exit from hard irq context
+ * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle
*
- * If the CPU was idle with dynamic ticks active, update the rdp->dynticks
- * to put let the RCU handling be aware that the CPU is going back to idle
- * with no ticks.
+ * If the current CPU is idle or running at a first-level (not nested)
+ * interrupt from idle, return true. The caller must have at least
+ * disabled preemption.
*/
-void rcu_irq_exit(void)
+int rcu_is_cpu_rrupt_from_idle(void)
{
- rcu_enter_nohz();
+ return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1;
}
#ifdef CONFIG_SMP
@@ -512,24 +625,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
#endif /* #ifdef CONFIG_SMP */
-#else /* #ifdef CONFIG_NO_HZ */
-
-#ifdef CONFIG_SMP
-
-static int dyntick_save_progress_counter(struct rcu_data *rdp)
-{
- return 0;
-}
-
-static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
-{
- return rcu_implicit_offline_qs(rdp);
-}
-
-#endif /* #ifdef CONFIG_SMP */
-
-#endif /* #else #ifdef CONFIG_NO_HZ */
-
int rcu_cpu_stall_suppress __read_mostly;
static void record_gp_stall_check_time(struct rcu_state *rsp)
@@ -1334,16 +1429,14 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
* (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
* Also schedule RCU core processing.
*
- * This function must be called with hardirqs disabled. It is normally
+ * This function must be called from hardirq context. It is normally
* invoked from the scheduling-clock interrupt. If rcu_pending returns
* false, there is no point in invoking rcu_check_callbacks().
*/
void rcu_check_callbacks(int cpu, int user)
{
trace_rcu_utilization("Start scheduler-tick");
- if (user ||
- (idle_cpu(cpu) && rcu_scheduler_active &&
- !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+ if (user || rcu_is_cpu_rrupt_from_idle()) {
/*
* Get here if this CPU took its interrupt from user
@@ -1913,9 +2006,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
for (i = 0; i < RCU_NEXT_SIZE; i++)
rdp->nxttail[i] = &rdp->nxtlist;
rdp->qlen = 0;
-#ifdef CONFIG_NO_HZ
rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
-#endif /* #ifdef CONFIG_NO_HZ */
+ WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != LLONG_MAX / 2);
+ WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
rdp->cpu = cpu;
rdp->rsp = rsp;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -1942,6 +2035,8 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rsp->n_force_qs;
rdp->blimit = blimit;
+ WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != LLONG_MAX / 2);
+ WARN_ON_ONCE((atomic_read(&rdp->dynticks->dynticks) & 0x1) != 1);
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
/*
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 517f2f8..0963fa15 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,9 +84,10 @@
* Dynticks per-CPU state.
*/
struct rcu_dynticks {
- int dynticks_nesting; /* Track irq/process nesting level. */
- int dynticks_nmi_nesting; /* Track NMI nesting level. */
- atomic_t dynticks; /* Even value for dynticks-idle, else odd. */
+ long long dynticks_nesting; /* Track irq/process nesting level. */
+ /* Process level is worth LLONG_MAX/2. */
+ int dynticks_nmi_nesting; /* Track NMI nesting level. */
+ atomic_t dynticks; /* Even value for idle, else odd. */
};
/* RCU's kthread states for tracing. */
@@ -274,16 +275,12 @@ struct rcu_data {
/* did other CPU force QS recently? */
long blimit; /* Upper limit on a processed batch */
-#ifdef CONFIG_NO_HZ
/* 3) dynticks interface. */
struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */
int dynticks_snap; /* Per-GP tracking for dynticks. */
-#endif /* #ifdef CONFIG_NO_HZ */
/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
-#ifdef CONFIG_NO_HZ
unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */
-#endif /* #ifdef CONFIG_NO_HZ */
unsigned long offline_fqs; /* Kicked due to being offline. */
unsigned long resched_ipi; /* Sent a resched IPI. */
@@ -307,11 +304,7 @@ struct rcu_data {
#define RCU_GP_INIT 1 /* Grace period being initialized. */
#define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */
#define RCU_FORCE_QS 3 /* Need to force quiescent state. */
-#ifdef CONFIG_NO_HZ
#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK
-#else /* #ifdef CONFIG_NO_HZ */
-#define RCU_SIGNAL_INIT RCU_FORCE_QS
-#endif /* #else #ifdef CONFIG_NO_HZ */
#define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 59c7bee..654cfe6 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -67,13 +67,11 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
rdp->completed, rdp->gpnum,
rdp->passed_quiesce, rdp->passed_quiesce_gpnum,
rdp->qs_pending);
-#ifdef CONFIG_NO_HZ
- seq_printf(m, " dt=%d/%d/%d df=%lu",
+ seq_printf(m, " dt=%d/%llx/%d df=%lu",
atomic_read(&rdp->dynticks->dynticks),
rdp->dynticks->dynticks_nesting,
rdp->dynticks->dynticks_nmi_nesting,
rdp->dynticks_fqs);
-#endif /* #ifdef CONFIG_NO_HZ */
seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
seq_printf(m, " ql=%ld qs=%c%c%c%c",
rdp->qlen,
@@ -141,13 +139,11 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
rdp->completed, rdp->gpnum,
rdp->passed_quiesce, rdp->passed_quiesce_gpnum,
rdp->qs_pending);
-#ifdef CONFIG_NO_HZ
- seq_printf(m, ",%d,%d,%d,%lu",
+ seq_printf(m, ",%d,%llx,%d,%lu",
atomic_read(&rdp->dynticks->dynticks),
rdp->dynticks->dynticks_nesting,
rdp->dynticks->dynticks_nmi_nesting,
rdp->dynticks_fqs);
-#endif /* #ifdef CONFIG_NO_HZ */
seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
seq_printf(m, ",%ld,\"%c%c%c%c\"", rdp->qlen,
".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
@@ -171,9 +167,7 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
static int show_rcudata_csv(struct seq_file *m, void *unused)
{
seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\",");
-#ifdef CONFIG_NO_HZ
seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\",");
-#endif /* #ifdef CONFIG_NO_HZ */
seq_puts(m, "\"of\",\"ri\",\"ql\",\"qs\"");
#ifdef CONFIG_RCU_BOOST
seq_puts(m, "\"kt\",\"ktl\"");
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 4042064..5d9d236 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -434,7 +434,6 @@ void tick_nohz_stop_sched_tick(int inidle)
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
- rcu_enter_nohz();
}
ts->idle_sleeps++;
@@ -473,6 +472,8 @@ out:
ts->last_jiffies = last_jiffies;
ts->sleep_length = ktime_sub(dev->next_event, now);
end:
+ if (inidle)
+ rcu_idle_enter();
local_irq_restore(flags);
}
@@ -529,6 +530,7 @@ void tick_nohz_restart_sched_tick(void)
ktime_t now;
local_irq_disable();
+ rcu_idle_exit();
if (ts->idle_active || (ts->inidle && ts->tick_stopped))
now = ktime_get();
@@ -543,8 +545,6 @@ void tick_nohz_restart_sched_tick(void)
ts->inidle = 0;
- rcu_exit_nohz();
-
/* Update jiffies first */
select_nohz_load_balancer(0);
tick_do_update_jiffies64(now);
OpenPOWER on IntegriCloud