rcu: Extend expedited funnel locking to rcu_data structure
The strictly rcu_node based funnel-locking scheme works well in many
cases, but systems with CONFIG_RCU_FANOUT_LEAF=64 won't necessarily get
all that much concurrency. This commit therefore extends the funnel
locking into the per-CPU rcu_data structure, providing concurrency equal
to the number of CPUs.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a905d3b..e45097fc 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3312,11 +3312,14 @@
/* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */
static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp,
+ struct rcu_data *rdp,
atomic_long_t *stat, unsigned long s)
{
if (rcu_exp_gp_seq_done(rsp, s)) {
if (rnp)
mutex_unlock(&rnp->exp_funnel_mutex);
+ else if (rdp)
+ mutex_unlock(&rdp->exp_funnel_mutex);
/* Ensure test happens before caller kfree(). */
smp_mb__before_atomic(); /* ^^^ */
atomic_long_inc(stat);
@@ -3332,6 +3335,7 @@
*/
static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
{
+ struct rcu_data *rdp;
struct rcu_node *rnp0;
struct rcu_node *rnp1 = NULL;
@@ -3343,16 +3347,24 @@
* can be inexact, as it is just promoting locality and is not
* strictly needed for correctness.
*/
- rnp0 = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode;
+ rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
+ if (sync_exp_work_done(rsp, NULL, NULL, &rsp->expedited_workdone1, s))
+ return NULL;
+ mutex_lock(&rdp->exp_funnel_mutex);
+ rnp0 = rdp->mynode;
for (; rnp0 != NULL; rnp0 = rnp0->parent) {
- if (sync_exp_work_done(rsp, rnp1, &rsp->expedited_workdone1, s))
+ if (sync_exp_work_done(rsp, rnp1, rdp,
+ &rsp->expedited_workdone2, s))
return NULL;
mutex_lock(&rnp0->exp_funnel_mutex);
if (rnp1)
mutex_unlock(&rnp1->exp_funnel_mutex);
+ else
+ mutex_unlock(&rdp->exp_funnel_mutex);
rnp1 = rnp0;
}
- if (sync_exp_work_done(rsp, rnp1, &rsp->expedited_workdone2, s))
+ if (sync_exp_work_done(rsp, rnp1, rdp,
+ &rsp->expedited_workdone3, s))
return NULL;
return rnp1;
}
@@ -3733,6 +3745,7 @@
WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
rdp->cpu = cpu;
rdp->rsp = rsp;
+ mutex_init(&rdp->exp_funnel_mutex);
rcu_boot_init_nocb_percpu_data(rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}