[PATCH v6 tip/core/rcu 02/17] rcu: Provide cond_resched_rcu_qs() to force quiescent states in long loops

From: Paul E. McKenney
Date: Fri Aug 15 2014 - 12:30:42 EST


From: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>

RCU-tasks requires the occasional voluntary context switch
from CPU-bound in-kernel tasks. In some cases, this requires
instrumenting cond_resched(). However, there is some reluctance
to countenance unconditionally instrumenting cond_resched() (see
http://lwn.net/Articles/603252/), so this commit creates a separate
cond_resched_rcu_qs() that may be used in place of cond_resched() in
locations prone to long-duration in-kernel looping.

This commit currently instruments only RCU-tasks. Future possibilities
include also instrumenting RCU, RCU-bh, and RCU-sched in order to reduce
IPI usage.

Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
---
fs/file.c | 2 +-
include/linux/rcupdate.h | 13 +++++++++++++
kernel/rcu/rcutorture.c | 4 ++--
kernel/rcu/tree.c | 12 ++++++------
kernel/rcu/tree_plugin.h | 2 +-
mm/mlock.c | 2 +-
6 files changed, 24 insertions(+), 11 deletions(-)

diff --git a/fs/file.c b/fs/file.c
index 66923fe3176e..1cafc4c9275b 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -367,7 +367,7 @@ static struct fdtable *close_files(struct files_struct * files)
struct file * file = xchg(&fdt->fd[i], NULL);
if (file) {
filp_close(file, files);
- cond_resched();
+ cond_resched_rcu_qs();
}
}
i++;
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 027a7228d6d3..41db3fca1e7f 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -330,6 +330,19 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
#define rcu_note_voluntary_context_switch(t) do { } while (0)
#endif /* #else #ifdef CONFIG_TASKS_RCU */

+/**
+ * cond_resched_rcu_qs - Report potential quiescent states to RCU
+ *
+ * This macro resembles cond_resched(), except that it is defined to
+ * report potential quiescent states to RCU-tasks even if the cond_resched()
+ * machinery were to be shut off, as some advocate for PREEMPT kernels.
+ */
+#define cond_resched_rcu_qs() \
+do { \
+ rcu_note_voluntary_context_switch(current); \
+ cond_resched(); \
+} while (0)
+
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
bool __rcu_is_watching(void);
#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 7fa34f86e5ba..febe07062ac5 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -667,7 +667,7 @@ static int rcu_torture_boost(void *arg)
}
call_rcu_time = jiffies;
}
- cond_resched();
+ cond_resched_rcu_qs();
stutter_wait("rcu_torture_boost");
if (torture_must_stop())
goto checkwait;
@@ -1019,7 +1019,7 @@ rcu_torture_reader(void *arg)
__this_cpu_inc(rcu_torture_batch[completed]);
preempt_enable();
cur_ops->readunlock(idx);
- cond_resched();
+ cond_resched_rcu_qs();
stutter_wait("rcu_torture_reader");
} while (!torture_must_stop());
if (irqreader && cur_ops->irq_capable) {
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f958c52f644d..645a33efc0d4 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1650,7 +1650,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
system_state == SYSTEM_RUNNING)
udelay(200);
#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
- cond_resched();
+ cond_resched_rcu_qs();
}

mutex_unlock(&rsp->onoff_mutex);
@@ -1739,7 +1739,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
/* smp_mb() provided by prior unlock-lock pair. */
nocb += rcu_future_gp_cleanup(rsp, rnp);
raw_spin_unlock_irq(&rnp->lock);
- cond_resched();
+ cond_resched_rcu_qs();
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
@@ -1788,7 +1788,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
/* Locking provides needed memory barrier. */
if (rcu_gp_init(rsp))
break;
- cond_resched();
+ cond_resched_rcu_qs();
flush_signals(current);
trace_rcu_grace_period(rsp->name,
ACCESS_ONCE(rsp->gpnum),
@@ -1831,10 +1831,10 @@ static int __noreturn rcu_gp_kthread(void *arg)
trace_rcu_grace_period(rsp->name,
ACCESS_ONCE(rsp->gpnum),
TPS("fqsend"));
- cond_resched();
+ cond_resched_rcu_qs();
} else {
/* Deal with stray signal. */
- cond_resched();
+ cond_resched_rcu_qs();
flush_signals(current);
trace_rcu_grace_period(rsp->name,
ACCESS_ONCE(rsp->gpnum),
@@ -2437,7 +2437,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
struct rcu_node *rnp;

rcu_for_each_leaf_node(rsp, rnp) {
- cond_resched();
+ cond_resched_rcu_qs();
mask = 0;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 02ac0fb186b8..a86a363ea453 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1842,7 +1842,7 @@ static int rcu_oom_notify(struct notifier_block *self,
get_online_cpus();
for_each_online_cpu(cpu) {
smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1);
- cond_resched();
+ cond_resched_rcu_qs();
}
put_online_cpus();

diff --git a/mm/mlock.c b/mm/mlock.c
index b1eb53634005..bc386a22d647 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -782,7 +782,7 @@ static int do_mlockall(int flags)

/* Ignore errors */
mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
- cond_resched();
+ cond_resched_rcu_qs();
}
out:
return 0;
--
1.8.1.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/