#include <linux/delay.h>
+/*
+ * Check the RCU kernel configuration parameters and print informative
+ * messages about anything out of the ordinary. If you like #ifdef, you
+ * will love this function.
+ */
+static void __init rcu_bootup_announce_oddness(void)
+{
+#ifdef CONFIG_RCU_TRACE
+ printk(KERN_INFO "\tRCU debugfs-based tracing is enabled.\n");
+#endif
+#if (defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || (!defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)
+ printk(KERN_INFO "\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
+ CONFIG_RCU_FANOUT);
+#endif
+#ifdef CONFIG_RCU_FANOUT_EXACT
+ printk(KERN_INFO "\tHierarchical RCU autobalancing is disabled.\n");
+#endif
+#ifdef CONFIG_RCU_FAST_NO_HZ
+ printk(KERN_INFO
+ "\tRCU dyntick-idle grace-period acceleration is enabled.\n");
+#endif
+#ifdef CONFIG_PROVE_RCU
+ printk(KERN_INFO "\tRCU lockdep checking is enabled.\n");
+#endif
+#ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
+ printk(KERN_INFO "\tRCU torture testing starts during boot.\n");
+#endif
+#ifndef CONFIG_RCU_CPU_STALL_DETECTOR
+ printk(KERN_INFO
+ "\tRCU-based detection of stalled CPUs is disabled.\n");
+#endif
+#ifndef CONFIG_RCU_CPU_STALL_VERBOSE
+ printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n");
+#endif
+#if NUM_RCU_LVL_4 != 0
+ printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n");
+#endif
+}
+
#ifdef CONFIG_TREE_PREEMPT_RCU
struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
*/
static void __init rcu_bootup_announce(void)
{
- printk(KERN_INFO
- "Experimental preemptable hierarchical RCU implementation.\n");
+ printk(KERN_INFO "Preemptable hierarchical RCU implementation.\n");
+ rcu_bootup_announce_oddness();
}
/*
* that this just means that the task currently running on the CPU is
* not in a quiescent state. There might be any number of tasks blocked
* while in an RCU read-side critical section.
+ *
+ * Unlike the other rcu_*_qs() functions, callers to this function
+ * must disable irqs in order to protect the assignment to
+ * ->rcu_read_unlock_special.
*/
static void rcu_preempt_qs(int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
+
rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
+ current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
}
/*
/* Possibly blocking in an RCU read-side critical section. */
rdp = rcu_preempt_state.rda[cpu];
rnp = rdp->mynode;
- spin_lock_irqsave(&rnp->lock, flags);
+ raw_spin_lock_irqsave(&rnp->lock, flags);
t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
t->rcu_blocked_node = rnp;
WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
phase = (rnp->gpnum + !(rnp->qsmask & rdp->grpmask)) & 0x1;
list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]);
- spin_unlock_irqrestore(&rnp->lock, flags);
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
* grace period, then the fact that the task has been enqueued
* means that we continue to block the current grace period.
*/
- rcu_preempt_qs(cpu);
local_irq_save(flags);
- t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+ rcu_preempt_qs(cpu);
local_irq_restore(flags);
}
struct rcu_node *rnp_p;
if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
- spin_unlock_irqrestore(&rnp->lock, flags);
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
return; /* Still need more quiescent states! */
}
/* Report up the rest of the hierarchy. */
mask = rnp->grpmask;
- spin_unlock(&rnp->lock); /* irqs remain disabled. */
- spin_lock(&rnp_p->lock); /* irqs already disabled. */
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ raw_spin_lock(&rnp_p->lock); /* irqs already disabled. */
rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
}
*/
special = t->rcu_read_unlock_special;
if (special & RCU_READ_UNLOCK_NEED_QS) {
- t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
rcu_preempt_qs(smp_processor_id());
}
*/
for (;;) {
rnp = t->rcu_blocked_node;
- spin_lock(&rnp->lock); /* irqs already disabled. */
+ raw_spin_lock(&rnp->lock); /* irqs already disabled. */
if (rnp == t->rcu_blocked_node)
break;
- spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
empty = !rcu_preempted_readers(rnp);
empty_exp = !rcu_preempted_readers_exp(rnp);
* Note that rcu_report_unblock_qs_rnp() releases rnp->lock.
*/
if (empty)
- spin_unlock_irqrestore(&rnp->lock, flags);
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
else
rcu_report_unblock_qs_rnp(rnp, flags);
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+#ifdef CONFIG_RCU_CPU_STALL_VERBOSE
+
+/*
+ * Dump detailed information for all tasks blocking the current RCU
+ * grace period on the specified rcu_node structure.
+ */
+static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
+{
+ unsigned long flags;
+ struct list_head *lp;
+ int phase;
+ struct task_struct *t;
+
+ if (rcu_preempted_readers(rnp)) {
+ raw_spin_lock_irqsave(&rnp->lock, flags);
+ phase = rnp->gpnum & 0x1;
+ lp = &rnp->blocked_tasks[phase];
+ list_for_each_entry(t, lp, rcu_node_entry)
+ sched_show_task(t);
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ }
+}
+
+/*
+ * Dump detailed information for all tasks blocking the current RCU
+ * grace period.
+ */
+static void rcu_print_detail_task_stall(struct rcu_state *rsp)
+{
+ struct rcu_node *rnp = rcu_get_root(rsp);
+
+ rcu_print_detail_task_stall_rnp(rnp);
+ rcu_for_each_leaf_node(rsp, rnp)
+ rcu_print_detail_task_stall_rnp(rnp);
+}
+
+#else /* #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */
+
+static void rcu_print_detail_task_stall(struct rcu_state *rsp)
+{
+}
+
+#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */
+
/*
* Scan the current list of tasks blocked within RCU read-side critical
* sections, printing out the tid of each.
*/
static void rcu_print_task_stall(struct rcu_node *rnp)
{
- unsigned long flags;
struct list_head *lp;
int phase;
struct task_struct *t;
if (rcu_preempted_readers(rnp)) {
- spin_lock_irqsave(&rnp->lock, flags);
phase = rnp->gpnum & 0x1;
lp = &rnp->blocked_tasks[phase];
list_for_each_entry(t, lp, rcu_node_entry)
printk(" P%d", t->pid);
- spin_unlock_irqrestore(&rnp->lock, flags);
}
}
lp_root = &rnp_root->blocked_tasks[i];
while (!list_empty(lp)) {
tp = list_entry(lp->next, typeof(*tp), rcu_node_entry);
- spin_lock(&rnp_root->lock); /* irqs already disabled */
+ raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
list_del(&tp->rcu_node_entry);
tp->rcu_blocked_node = rnp_root;
list_add(&tp->rcu_node_entry, lp_root);
- spin_unlock(&rnp_root->lock); /* irqs remain disabled */
+ raw_spin_unlock(&rnp_root->lock); /* irqs remain disabled */
}
}
return retval;
struct task_struct *t = current;
if (t->rcu_read_lock_nesting == 0) {
- t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
rcu_preempt_qs(cpu);
return;
}
if (!rcu_scheduler_active)
return;
+ init_rcu_head_on_stack(&rcu.head);
init_completion(&rcu.completion);
/* Will wake me after RCU finished. */
call_rcu(&rcu.head, wakeme_after_rcu);
/* Wait for it. */
wait_for_completion(&rcu.completion);
+ destroy_rcu_head_on_stack(&rcu.head);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
unsigned long flags;
unsigned long mask;
- spin_lock_irqsave(&rnp->lock, flags);
+ raw_spin_lock_irqsave(&rnp->lock, flags);
for (;;) {
if (!sync_rcu_preempt_exp_done(rnp))
break;
break;
}
mask = rnp->grpmask;
- spin_unlock(&rnp->lock); /* irqs remain disabled */
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
rnp = rnp->parent;
- spin_lock(&rnp->lock); /* irqs already disabled */
+ raw_spin_lock(&rnp->lock); /* irqs already disabled */
rnp->expmask &= ~mask;
}
- spin_unlock_irqrestore(&rnp->lock, flags);
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
{
int must_wait;
- spin_lock(&rnp->lock); /* irqs already disabled */
+ raw_spin_lock(&rnp->lock); /* irqs already disabled */
list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]);
list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]);
must_wait = rcu_preempted_readers_exp(rnp);
- spin_unlock(&rnp->lock); /* irqs remain disabled */
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
if (!must_wait)
rcu_report_exp_rnp(rsp, rnp);
}
/* force all RCU readers onto blocked_tasks[]. */
synchronize_sched_expedited();
- spin_lock_irqsave(&rsp->onofflock, flags);
+ raw_spin_lock_irqsave(&rsp->onofflock, flags);
/* Initialize ->expmask for all non-leaf rcu_node structures. */
rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
- spin_lock(&rnp->lock); /* irqs already disabled. */
+ raw_spin_lock(&rnp->lock); /* irqs already disabled. */
rnp->expmask = rnp->qsmaskinit;
- spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
/* Snapshot current state of ->blocked_tasks[] lists. */
if (NUM_RCU_NODES > 1)
sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp));
- spin_unlock_irqrestore(&rsp->onofflock, flags);
+ raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
/* Wait for snapshotted ->blocked_tasks[] lists to drain. */
rnp = rcu_get_root(rsp);
static void __init rcu_bootup_announce(void)
{
printk(KERN_INFO "Hierarchical RCU implementation.\n");
+ rcu_bootup_announce_oddness();
}
/*
/* Because preemptible RCU does not exist, no quieting of tasks. */
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
{
- spin_unlock_irqrestore(&rnp->lock, flags);
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
* Because preemptable RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections.
*/
+static void rcu_print_detail_task_stall(struct rcu_state *rsp)
+{
+}
+
+/*
+ * Because preemptable RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections.
+ */
static void rcu_print_task_stall(struct rcu_node *rnp)
{
}
}
#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
+
+#if !defined(CONFIG_RCU_FAST_NO_HZ)
+
+/*
+ * Check to see if any future RCU-related work will need to be done
+ * by the current CPU, even if none need be done immediately, returning
+ * 1 if so. This function is part of the RCU implementation; it is -not-
+ * an exported member of the RCU API.
+ *
+ * Because we have preemptible RCU, just check whether this CPU needs
+ * any flavor of RCU. Do not chew up lots of CPU cycles with preemption
+ * disabled in a most-likely vain attempt to cause RCU not to need this CPU.
+ */
+int rcu_needs_cpu(int cpu)
+{
+ return rcu_needs_cpu_quick_check(cpu);
+}
+
+/*
+ * Check to see if we need to continue a callback-flush operations to
+ * allow the last CPU to enter dyntick-idle mode. But fast dyntick-idle
+ * entry is not configured, so we never do need to.
+ */
+static void rcu_needs_cpu_flush(void)
+{
+}
+
+#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
+
+#define RCU_NEEDS_CPU_FLUSHES 5
+static DEFINE_PER_CPU(int, rcu_dyntick_drain);
+static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
+
+/*
+ * Check to see if any future RCU-related work will need to be done
+ * by the current CPU, even if none need be done immediately, returning
+ * 1 if so. This function is part of the RCU implementation; it is -not-
+ * an exported member of the RCU API.
+ *
+ * Because we are not supporting preemptible RCU, attempt to accelerate
+ * any current grace periods so that RCU no longer needs this CPU, but
+ * only if all other CPUs are already in dynticks-idle mode. This will
+ * allow the CPU cores to be powered down immediately, as opposed to after
+ * waiting many milliseconds for grace periods to elapse.
+ *
+ * Because it is not legal to invoke rcu_process_callbacks() with irqs
+ * disabled, we do one pass of force_quiescent_state(), then do a
+ * raise_softirq() to cause rcu_process_callbacks() to be invoked later.
+ * The per-cpu rcu_dyntick_drain variable controls the sequencing.
+ */
+int rcu_needs_cpu(int cpu)
+{
+ int c = 0;
+ int snap;
+ int snap_nmi;
+ int thatcpu;
+
+ /* Check for being in the holdoff period. */
+ if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies)
+ return rcu_needs_cpu_quick_check(cpu);
+
+ /* Don't bother unless we are the last non-dyntick-idle CPU. */
+ for_each_online_cpu(thatcpu) {
+ if (thatcpu == cpu)
+ continue;
+ snap = per_cpu(rcu_dynticks, thatcpu).dynticks;
+ snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi;
+ smp_mb(); /* Order sampling of snap with end of grace period. */
+ if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) {
+ per_cpu(rcu_dyntick_drain, cpu) = 0;
+ per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
+ return rcu_needs_cpu_quick_check(cpu);
+ }
+ }
+
+ /* Check and update the rcu_dyntick_drain sequencing. */
+ if (per_cpu(rcu_dyntick_drain, cpu) <= 0) {
+ /* First time through, initialize the counter. */
+ per_cpu(rcu_dyntick_drain, cpu) = RCU_NEEDS_CPU_FLUSHES;
+ } else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
+ /* We have hit the limit, so time to give up. */
+ per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
+ return rcu_needs_cpu_quick_check(cpu);
+ }
+
+ /* Do one step pushing remaining RCU callbacks through. */
+ if (per_cpu(rcu_sched_data, cpu).nxtlist) {
+ rcu_sched_qs(cpu);
+ force_quiescent_state(&rcu_sched_state, 0);
+ c = c || per_cpu(rcu_sched_data, cpu).nxtlist;
+ }
+ if (per_cpu(rcu_bh_data, cpu).nxtlist) {
+ rcu_bh_qs(cpu);
+ force_quiescent_state(&rcu_bh_state, 0);
+ c = c || per_cpu(rcu_bh_data, cpu).nxtlist;
+ }
+
+ /* If RCU callbacks are still pending, RCU still needs this CPU. */
+ if (c)
+ raise_softirq(RCU_SOFTIRQ);
+ return c;
+}
+
+/*
+ * Check to see if we need to continue a callback-flush operations to
+ * allow the last CPU to enter dyntick-idle mode.
+ */
+static void rcu_needs_cpu_flush(void)
+{
+ int cpu = smp_processor_id();
+ unsigned long flags;
+
+ if (per_cpu(rcu_dyntick_drain, cpu) <= 0)
+ return;
+ local_irq_save(flags);
+ (void)rcu_needs_cpu(cpu);
+ local_irq_restore(flags);
+}
+
+#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */