* Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
+#include <linux/delay.h>
#ifdef CONFIG_TREE_PREEMPT_RCU
struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
+static int rcu_preempted_readers_exp(struct rcu_node *rnp);
+
/*
* Tell them what RCU they are running.
*/
EXPORT_SYMBOL_GPL(rcu_batches_completed);
/*
+ * Force a quiescent state for preemptible RCU.
+ */
+void rcu_force_quiescent_state(void)
+{
+ force_quiescent_state(&rcu_preempt_state, 0);
+}
+EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
+
+/*
* Record a preemptable-RCU quiescent state for the specified CPU. Note
* 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
/* 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);
}
/*
*/
static int rcu_preempted_readers(struct rcu_node *rnp)
{
- return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
+ int phase = rnp->gpnum & 0x1;
+
+ return !list_empty(&rnp->blocked_tasks[phase]) ||
+ !list_empty(&rnp->blocked_tasks[phase + 2]);
}
/*
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);
}
static void rcu_read_unlock_special(struct task_struct *t)
{
int empty;
+ int empty_exp;
unsigned long flags;
struct rcu_node *rnp;
int special;
*/
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);
+ smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
list_del_init(&t->rcu_node_entry);
t->rcu_blocked_node = NULL;
* 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);
+
+ /*
+ * If this was the last task on the expedited lists,
+ * then we need to report up the rcu_node hierarchy.
+ */
+ if (!empty_exp && !rcu_preempted_readers_exp(rnp))
+ rcu_report_exp_rnp(&rcu_preempt_state, rnp);
} else {
local_irq_restore(flags);
}
if (--ACCESS_ONCE(t->rcu_read_lock_nesting) == 0 &&
unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
rcu_read_unlock_special(t);
+#ifdef CONFIG_PROVE_LOCKING
+ WARN_ON_ONCE(ACCESS_ONCE(t->rcu_read_lock_nesting) < 0);
+#endif /* #ifdef CONFIG_PROVE_LOCKING */
}
EXPORT_SYMBOL_GPL(__rcu_read_unlock);
#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);
}
}
int i;
struct list_head *lp;
struct list_head *lp_root;
- int retval;
+ int retval = 0;
struct rcu_node *rnp_root = rcu_get_root(rsp);
struct task_struct *tp;
}
WARN_ON_ONCE(rnp != rdp->mynode &&
(!list_empty(&rnp->blocked_tasks[0]) ||
- !list_empty(&rnp->blocked_tasks[1])));
+ !list_empty(&rnp->blocked_tasks[1]) ||
+ !list_empty(&rnp->blocked_tasks[2]) ||
+ !list_empty(&rnp->blocked_tasks[3])));
/*
* Move tasks up to root rcu_node. Rely on the fact that the
* rcu_nodes in terms of gp_num value. This fact allows us to
* move the blocked_tasks[] array directly, element by element.
*/
- retval = rcu_preempted_readers(rnp);
- for (i = 0; i < 2; i++) {
+ if (rcu_preempted_readers(rnp))
+ retval |= RCU_OFL_TASKS_NORM_GP;
+ if (rcu_preempted_readers_exp(rnp))
+ retval |= RCU_OFL_TASKS_EXP_GP;
+ for (i = 0; i < 4; i++) {
lp = &rnp->blocked_tasks[i];
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;
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
+static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
+static long sync_rcu_preempt_exp_count;
+static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
+
+/*
+ * Return non-zero if there are any tasks in RCU read-side critical
+ * sections blocking the current preemptible-RCU expedited grace period.
+ * If there is no preemptible-RCU expedited grace period currently in
+ * progress, returns zero unconditionally.
+ */
+static int rcu_preempted_readers_exp(struct rcu_node *rnp)
+{
+ return !list_empty(&rnp->blocked_tasks[2]) ||
+ !list_empty(&rnp->blocked_tasks[3]);
+}
+
+/*
+ * return non-zero if there is no RCU expedited grace period in progress
+ * for the specified rcu_node structure, in other words, if all CPUs and
+ * tasks covered by the specified rcu_node structure have done their bit
+ * for the current expedited grace period. Works only for preemptible
+ * RCU -- other RCU implementation use other means.
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex.
+ */
+static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
+{
+ return !rcu_preempted_readers_exp(rnp) &&
+ ACCESS_ONCE(rnp->expmask) == 0;
+}
+
+/*
+ * Report the exit from RCU read-side critical section for the last task
+ * that queued itself during or before the current expedited preemptible-RCU
+ * grace period. This event is reported either to the rcu_node structure on
+ * which the task was queued or to one of that rcu_node structure's ancestors,
+ * recursively up the tree. (Calm down, calm down, we do the recursion
+ * iteratively!)
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex.
+ */
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+ unsigned long flags;
+ unsigned long mask;
+
+ raw_spin_lock_irqsave(&rnp->lock, flags);
+ for (;;) {
+ if (!sync_rcu_preempt_exp_done(rnp))
+ break;
+ if (rnp->parent == NULL) {
+ wake_up(&sync_rcu_preempt_exp_wq);
+ break;
+ }
+ mask = rnp->grpmask;
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
+ rnp = rnp->parent;
+ raw_spin_lock(&rnp->lock); /* irqs already disabled */
+ rnp->expmask &= ~mask;
+ }
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+/*
+ * Snapshot the tasks blocking the newly started preemptible-RCU expedited
+ * grace period for the specified rcu_node structure. If there are no such
+ * tasks, report it up the rcu_node hierarchy.
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex and rsp->onofflock.
+ */
+static void
+sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+ int must_wait;
+
+ 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);
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
+ if (!must_wait)
+ rcu_report_exp_rnp(rsp, rnp);
+}
+
/*
- * Wait for an rcu-preempt grace period. We are supposed to expedite the
- * grace period, but this is the crude slow compatability hack, so just
- * invoke synchronize_rcu().
+ * Wait for an rcu-preempt grace period, but expedite it. The basic idea
+ * is to invoke synchronize_sched_expedited() to push all the tasks to
+ * the ->blocked_tasks[] lists, move all entries from the first set of
+ * ->blocked_tasks[] lists to the second set, and finally wait for this
+ * second set to drain.
*/
void synchronize_rcu_expedited(void)
{
- synchronize_rcu();
+ unsigned long flags;
+ struct rcu_node *rnp;
+ struct rcu_state *rsp = &rcu_preempt_state;
+ long snap;
+ int trycount = 0;
+
+ smp_mb(); /* Caller's modifications seen first by other CPUs. */
+ snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1;
+ smp_mb(); /* Above access cannot bleed into critical section. */
+
+ /*
+ * Acquire lock, falling back to synchronize_rcu() if too many
+ * lock-acquisition failures. Of course, if someone does the
+ * expedited grace period for us, just leave.
+ */
+ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
+ if (trycount++ < 10)
+ udelay(trycount * num_online_cpus());
+ else {
+ synchronize_rcu();
+ return;
+ }
+ if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
+ goto mb_ret; /* Others did our work for us. */
+ }
+ if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
+ goto unlock_mb_ret; /* Others did our work for us. */
+
+ /* force all RCU readers onto blocked_tasks[]. */
+ synchronize_sched_expedited();
+
+ 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) {
+ raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ rnp->expmask = rnp->qsmaskinit;
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ }
+
+ /* Snapshot current state of ->blocked_tasks[] lists. */
+ rcu_for_each_leaf_node(rsp, rnp)
+ sync_rcu_preempt_exp_init(rsp, rnp);
+ if (NUM_RCU_NODES > 1)
+ sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp));
+
+ raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
+
+ /* Wait for snapshotted ->blocked_tasks[] lists to drain. */
+ rnp = rcu_get_root(rsp);
+ wait_event(sync_rcu_preempt_exp_wq,
+ sync_rcu_preempt_exp_done(rnp));
+
+ /* Clean up and exit. */
+ smp_mb(); /* ensure expedited GP seen before counter increment. */
+ ACCESS_ONCE(sync_rcu_preempt_exp_count)++;
+unlock_mb_ret:
+ mutex_unlock(&sync_rcu_preempt_exp_mutex);
+mb_ret:
+ smp_mb(); /* ensure subsequent action seen after grace period. */
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
EXPORT_SYMBOL_GPL(rcu_batches_completed);
/*
+ * Force a quiescent state for RCU, which, because there is no preemptible
+ * RCU, becomes the same as rcu-sched.
+ */
+void rcu_force_quiescent_state(void)
+{
+ rcu_sched_force_quiescent_state();
+}
+EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
+
+/*
* Because preemptable RCU does not exist, we never have to check for
* CPUs being in quiescent states.
*/
/* 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)
{
}
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Because preemptable RCU does not exist, there is never any need to
+ * report on tasks preempted in RCU read-side critical sections during
+ * expedited RCU grace periods.
+ */
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+ return;
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
/*
* Because preemptable RCU does not exist, it never has any work to do.
*/
}
#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 thatcpu;
+
+ /* Don't bother unless we are the last non-dyntick-idle CPU. */
+ for_each_cpu_not(thatcpu, nohz_cpu_mask)
+ if (thatcpu != cpu) {
+ 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);
+ per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
+ }
+ 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) */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff