* not in a quiescent state. There might be any number of tasks blocked
* while in an RCU read-side critical section.
*/
-static void rcu_preempt_qs_record(int cpu)
+static void rcu_preempt_qs(int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
- rdp->passed_quiesc = 1;
rdp->passed_quiesc_completed = rdp->completed;
+ barrier();
+ rdp->passed_quiesc = 1;
}
/*
- * We have entered the scheduler or are between softirqs in ksoftirqd.
- * If we are in an RCU read-side critical section, we need to reflect
- * that in the state of the rcu_node structure corresponding to this CPU.
- * Caller must disable hardirqs.
+ * We have entered the scheduler, and the current task might soon be
+ * context-switched away from. If this task is in an RCU read-side
+ * critical section, we will no longer be able to rely on the CPU to
+ * record that fact, so we enqueue the task on the appropriate entry
+ * of the blocked_tasks[] array. The task will dequeue itself when
+ * it exits the outermost enclosing RCU read-side critical section.
+ * Therefore, the current grace period cannot be permitted to complete
+ * until the blocked_tasks[] entry indexed by the low-order bit of
+ * rnp->gpnum empties.
+ *
+ * Caller must disable preemption.
*/
-static void rcu_preempt_qs(int cpu)
+static void rcu_preempt_note_context_switch(int cpu)
{
struct task_struct *t = current;
+ unsigned long flags;
int phase;
struct rcu_data *rdp;
struct rcu_node *rnp;
/* Possibly blocking in an RCU read-side critical section. */
rdp = rcu_preempt_state.rda[cpu];
rnp = rdp->mynode;
- spin_lock(&rnp->lock);
+ spin_lock_irqsave(&rnp->lock, flags);
t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
- t->rcu_blocked_cpu = cpu;
+ t->rcu_blocked_node = rnp;
/*
* If this CPU has already checked in, then this task
* state for the current grace period), then as long
* as that task remains queued, the current grace period
* cannot end.
+ *
+ * But first, note that the current CPU must still be
+ * on line!
*/
- phase = !(rnp->qsmask & rdp->grpmask) ^ (rnp->gpnum & 0x1);
+ WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);
+ 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]);
- smp_mb(); /* Ensure later ctxt swtch seen after above. */
- spin_unlock(&rnp->lock);
+ 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_record(cpu);
- t->rcu_read_unlock_special &= ~(RCU_READ_UNLOCK_NEED_QS |
- RCU_READ_UNLOCK_GOT_QS);
+ rcu_preempt_qs(cpu);
+ local_irq_save(flags);
+ t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+ local_irq_restore(flags);
}
/*
}
EXPORT_SYMBOL_GPL(__rcu_read_lock);
+/*
+ * Check for preempted RCU readers blocking the current grace period
+ * for the specified rcu_node structure. If the caller needs a reliable
+ * answer, it must hold the rcu_node's ->lock.
+ */
+static int rcu_preempted_readers(struct rcu_node *rnp)
+{
+ return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
+}
+
static void rcu_read_unlock_special(struct task_struct *t)
{
int empty;
special = t->rcu_read_unlock_special;
if (special & RCU_READ_UNLOCK_NEED_QS) {
t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
- t->rcu_read_unlock_special |= RCU_READ_UNLOCK_GOT_QS;
+ rcu_preempt_qs(smp_processor_id());
}
/* Hardware IRQ handlers cannot block. */
if (special & RCU_READ_UNLOCK_BLOCKED) {
t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;
- /* Remove this task from the list it blocked on. */
- rnp = rcu_preempt_state.rda[t->rcu_blocked_cpu]->mynode;
- spin_lock(&rnp->lock);
- empty = list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
+ /*
+ * Remove this task from the list it blocked on. The
+ * task can migrate while we acquire the lock, but at
+ * most one time. So at most two passes through loop.
+ */
+ for (;;) {
+ rnp = t->rcu_blocked_node;
+ spin_lock(&rnp->lock); /* irqs already disabled. */
+ if (rnp == t->rcu_blocked_node)
+ break;
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ }
+ empty = !rcu_preempted_readers(rnp);
list_del_init(&t->rcu_node_entry);
- t->rcu_blocked_cpu = -1;
+ t->rcu_blocked_node = NULL;
/*
* If this was the last task on the current list, and if
* drop rnp->lock and restore irq.
*/
if (!empty && rnp->qsmask == 0 &&
- list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1])) {
- t->rcu_read_unlock_special &=
- ~(RCU_READ_UNLOCK_NEED_QS |
- RCU_READ_UNLOCK_GOT_QS);
+ !rcu_preempted_readers(rnp)) {
+ struct rcu_node *rnp_p;
+
if (rnp->parent == NULL) {
/* Only one rcu_node in the tree. */
cpu_quiet_msk_finish(&rcu_preempt_state, flags);
/* Report up the rest of the hierarchy. */
mask = rnp->grpmask;
spin_unlock_irqrestore(&rnp->lock, flags);
- rnp = rnp->parent;
- spin_lock_irqsave(&rnp->lock, flags);
- cpu_quiet_msk(mask, &rcu_preempt_state, rnp, flags);
+ rnp_p = rnp->parent;
+ spin_lock_irqsave(&rnp_p->lock, flags);
+ WARN_ON_ONCE(rnp->qsmask);
+ cpu_quiet_msk(mask, &rcu_preempt_state, rnp_p, flags);
return;
}
spin_unlock(&rnp->lock);
{
unsigned long flags;
struct list_head *lp;
- int phase = rnp->gpnum & 0x1;
+ int phase;
struct task_struct *t;
- if (!list_empty(&rnp->blocked_tasks[phase])) {
+ if (rcu_preempted_readers(rnp)) {
spin_lock_irqsave(&rnp->lock, flags);
- phase = rnp->gpnum & 0x1; /* re-read under lock. */
+ phase = rnp->gpnum & 0x1;
lp = &rnp->blocked_tasks[phase];
list_for_each_entry(t, lp, rcu_node_entry)
printk(" P%d", t->pid);
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
/*
- * Check for preempted RCU readers for the specified rcu_node structure.
- * If the caller needs a reliable answer, it must hold the rcu_node's
- * >lock.
+ * Check that the list of blocked tasks for the newly completed grace
+ * period is in fact empty. It is a serious bug to complete a grace
+ * period that still has RCU readers blocked! This function must be
+ * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
+ * must be held by the caller.
*/
-static int rcu_preempted_readers(struct rcu_node *rnp)
+static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
- return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
+ WARN_ON_ONCE(rcu_preempted_readers(rnp));
+ WARN_ON_ONCE(rnp->qsmask);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Handle tasklist migration for case in which all CPUs covered by the
+ * specified rcu_node have gone offline. Move them up to the root
+ * rcu_node. The reason for not just moving them to the immediate
+ * parent is to remove the need for rcu_read_unlock_special() to
+ * make more than two attempts to acquire the target rcu_node's lock.
+ *
+ * Returns 1 if there was previously a task blocking the current grace
+ * period on the specified rcu_node structure.
+ *
+ * The caller must hold rnp->lock with irqs disabled.
+ */
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp)
+{
+ int i;
+ struct list_head *lp;
+ struct list_head *lp_root;
+ int retval = rcu_preempted_readers(rnp);
+ struct rcu_node *rnp_root = rcu_get_root(rsp);
+ struct task_struct *tp;
+
+ if (rnp == rnp_root) {
+ WARN_ONCE(1, "Last CPU thought to be offlined?");
+ return 0; /* Shouldn't happen: at least one CPU online. */
+ }
+ WARN_ON_ONCE(rnp != rdp->mynode &&
+ (!list_empty(&rnp->blocked_tasks[0]) ||
+ !list_empty(&rnp->blocked_tasks[1])));
+
+ /*
+ * Move tasks up to root rcu_node. Rely on the fact that the
+ * root rcu_node can be at most one ahead of the rest of the
+ * rcu_nodes in terms of gp_num value. This fact allows us to
+ * move the blocked_tasks[] array directly, element by element.
+ */
+ for (i = 0; i < 2; 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 */
+ 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 */
+ }
+ }
+
+ return retval;
}
/*
+ * Do CPU-offline processing for preemptable RCU.
+ */
+static void rcu_preempt_offline_cpu(int cpu)
+{
+ __rcu_offline_cpu(cpu, &rcu_preempt_state);
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
* Check for a quiescent state from the current CPU. When a task blocks,
* the task is recorded in the corresponding CPU's rcu_node structure,
* which is checked elsewhere.
struct task_struct *t = current;
if (t->rcu_read_lock_nesting == 0) {
- t->rcu_read_unlock_special &=
- ~(RCU_READ_UNLOCK_NEED_QS | RCU_READ_UNLOCK_GOT_QS);
- rcu_preempt_qs_record(cpu);
+ t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+ rcu_preempt_qs(cpu);
return;
}
- if (per_cpu(rcu_preempt_data, cpu).qs_pending) {
- if (t->rcu_read_unlock_special & RCU_READ_UNLOCK_GOT_QS) {
- rcu_preempt_qs_record(cpu);
- t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_GOT_QS;
- } else if (!(t->rcu_read_unlock_special &
- RCU_READ_UNLOCK_NEED_QS)) {
- t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
- }
- }
+ if (per_cpu(rcu_preempt_data, cpu).qs_pending)
+ t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
}
/*
EXPORT_SYMBOL_GPL(call_rcu);
/*
+ * 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().
+ */
+void synchronize_rcu_expedited(void)
+{
+ synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
* Check to see if there is any immediate preemptable-RCU-related work
* to be done.
*/
return !!per_cpu(rcu_preempt_data, cpu).nxtlist;
}
+/**
+ * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
+ */
+void rcu_barrier(void)
+{
+ _rcu_barrier(&rcu_preempt_state, call_rcu);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier);
+
/*
* Initialize preemptable RCU's per-CPU data.
*/
}
/*
+ * Move preemptable RCU's callbacks to ->orphan_cbs_list.
+ */
+static void rcu_preempt_send_cbs_to_orphanage(void)
+{
+ rcu_send_cbs_to_orphanage(&rcu_preempt_state);
+}
+
+/*
+ * Initialize preemptable RCU's state structures.
+ */
+static void __init __rcu_init_preempt(void)
+{
+ RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data);
+}
+
+/*
* Check for a task exiting while in a preemptable-RCU read-side
* critical section, clean up if so. No need to issue warnings,
* as debug_check_no_locks_held() already does this if lockdep
* Because preemptable RCU does not exist, we never have to check for
* CPUs being in quiescent states.
*/
-static void rcu_preempt_qs(int cpu)
+static void rcu_preempt_note_context_switch(int cpu)
{
}
+/*
+ * Because preemptable RCU does not exist, there are never any preempted
+ * RCU readers.
+ */
+static int rcu_preempted_readers(struct rcu_node *rnp)
+{
+ return 0;
+}
+
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
/*
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
/*
- * Because preemptable RCU does not exist, there are never any preempted
- * RCU readers.
+ * Because there is no preemptable RCU, there can be no readers blocked,
+ * so there is no need to check for blocked tasks. So check only for
+ * bogus qsmask values.
*/
-static int rcu_preempted_readers(struct rcu_node *rnp)
+static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+{
+ WARN_ON_ONCE(rnp->qsmask);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Because preemptable RCU does not exist, it never needs to migrate
+ * tasks that were blocked within RCU read-side critical sections, and
+ * such non-existent tasks cannot possibly have been blocking the current
+ * grace period.
+ */
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp)
{
return 0;
}
/*
+ * Because preemptable RCU does not exist, it never needs CPU-offline
+ * processing.
+ */
+static void rcu_preempt_offline_cpu(int cpu)
+{
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
* Because preemptable RCU does not exist, it never has any callbacks
* to check.
*/
-void rcu_preempt_check_callbacks(int cpu)
+static void rcu_preempt_check_callbacks(int cpu)
{
}
* Because preemptable RCU does not exist, it never has any callbacks
* to process.
*/
-void rcu_preempt_process_callbacks(void)
+static void rcu_preempt_process_callbacks(void)
{
}
EXPORT_SYMBOL_GPL(call_rcu);
/*
+ * Wait for an rcu-preempt grace period, but make it happen quickly.
+ * But because preemptable RCU does not exist, map to rcu-sched.
+ */
+void synchronize_rcu_expedited(void)
+{
+ synchronize_sched_expedited();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
* Because preemptable RCU does not exist, it never has any work to do.
*/
static int rcu_preempt_pending(int cpu)
}
/*
+ * Because preemptable RCU does not exist, rcu_barrier() is just
+ * another name for rcu_barrier_sched().
+ */
+void rcu_barrier(void)
+{
+ rcu_barrier_sched();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier);
+
+/*
* Because preemptable RCU does not exist, there is no per-CPU
* data to initialize.
*/
{
}
+/*
+ * Because there is no preemptable RCU, there are no callbacks to move.
+ */
+static void rcu_preempt_send_cbs_to_orphanage(void)
+{
+}
+
+/*
+ * Because preemptable RCU does not exist, it need not be initialized.
+ */
+static void __init __rcu_init_preempt(void)
+{
+}
+
#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff