rcu: Add expedited grace-period support for preemptible RCU
Implement an synchronize_rcu_expedited() for preemptible RCU
that actually is expedited. This uses
synchronize_sched_expedited() to force all threads currently
running in a preemptible-RCU read-side critical section onto the
appropriate ->blocked_tasks[] list, then takes a snapshot of all
of these lists and waits for them to drain.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1259784616158-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index c9f0c97..37fbccd 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -24,12 +24,15 @@
* 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.
*/
@@ -157,7 +160,10 @@
*/
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]);
}
/*
@@ -204,6 +210,7 @@
static void rcu_read_unlock_special(struct task_struct *t)
{
int empty;
+ int empty_exp;
unsigned long flags;
struct rcu_node *rnp;
int special;
@@ -247,6 +254,8 @@
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;
@@ -259,6 +268,13 @@
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);
}
@@ -343,7 +359,7 @@
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;
@@ -353,7 +369,9 @@
}
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
@@ -361,8 +379,11 @@
* 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)) {
@@ -449,14 +470,159 @@
}
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);
+
/*
- * 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().
+ * 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;
+
+ 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;
+ spin_unlock(&rnp->lock); /* irqs remain disabled */
+ rnp = rnp->parent;
+ spin_lock(&rnp->lock); /* irqs already disabled */
+ rnp->expmask &= ~mask;
+ }
+ 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;
+
+ 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 */
+ if (!must_wait)
+ rcu_report_exp_rnp(rsp, rnp);
+}
+
+/*
+ * 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();
+
+ 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. */
+ rnp->expmask = rnp->qsmaskinit;
+ 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));
+
+ 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);
@@ -655,6 +821,20 @@
}
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.
*/