sched: Fix init NOHZ_IDLE flag

On my SMP platform which is made of 5 cores in 2 clusters, I
have the nr_busy_cpu field of sched_group_power struct that is
not null when the platform is fully idle - which makes the
scheduler unhappy.

The root cause is:

During the boot sequence, some CPUs reach the idle loop and set
their NOHZ_IDLE flag while waiting for others CPUs to boot. But
the nr_busy_cpus field is initialized later with the assumption
that all CPUs are in the busy state whereas some CPUs have
already set their NOHZ_IDLE flag.

More generally, the NOHZ_IDLE flag must be initialized when new
sched_domains are created in order to ensure that NOHZ_IDLE and
nr_busy_cpus are aligned.

This condition can be ensured by adding a synchronize_rcu()
between the destruction of old sched_domains and the creation of
new ones so the NOHZ_IDLE flag will not be updated with old
sched_domain once it has been initialized. But this solution
introduces a additionnal latency in the rebuild sequence that is
called during cpu hotplug.

As suggested by Frederic Weisbecker, another solution is to have
the same rcu lifecycle for both NOHZ_IDLE and sched_domain
struct. A new nohz_idle field is added to sched_domain so both
status and sched_domain will share the same RCU lifecycle and
will be always synchronized. In addition, there is no more need
to protect nohz_idle against concurrent access as it is only
modified by 2 exclusive functions called by local cpu.

This solution has been prefered to the creation of a new struct
with an extra pointer indirection for sched_domain.

The synchronization is done at the cost of :

 - An additional indirection and a rcu_dereference for accessing nohz_idle.
 - We use only the nohz_idle field of the top sched_domain.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: linaro-kernel@lists.linaro.org
Cc: peterz@infradead.org
Cc: fweisbec@gmail.com
Cc: pjt@google.com
Cc: rostedt@goodmis.org
Cc: efault@gmx.de
Link: http://lkml.kernel.org/r/1366729142-14662-1-git-send-email-vincent.guittot@linaro.org
[ Fixed !NO_HZ build bug. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6bdaa73ede13abb0f7a8bd11b43776a153874f4e..a25168f4ab8603a05800484d175856eee9ba48f9 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -808,6 +808,8 @@ struct sched_domain {
        unsigned int wake_idx;
        unsigned int forkexec_idx;
        unsigned int smt_gain;
+
+       int nohz_idle;                  /* NOHZ IDLE status */
        int flags;                      /* See SD_* */
        int level;
 

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index acaf567a03d29f5e0cee33bafcf9b97020344d47..8bf7081b1ec5201af66b08eaf3602177beef6368 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5420,13 +5420,16 @@ static inline void set_cpu_sd_state_busy(void)
        struct sched_domain *sd;
        int cpu = smp_processor_id();
 
-       if (!test_bit(NOHZ_IDLE, nohz_flags(cpu)))
-               return;
-       clear_bit(NOHZ_IDLE, nohz_flags(cpu));
-
        rcu_read_lock();
-       for_each_domain(cpu, sd)
+       sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd);
+
+       if (!sd || !sd->nohz_idle)
+               goto unlock;
+       sd->nohz_idle = 0;
+
+       for (; sd; sd = sd->parent)
                atomic_inc(&sd->groups->sgp->nr_busy_cpus);
+unlock:
        rcu_read_unlock();
 }
 
@@ -5435,13 +5438,16 @@ void set_cpu_sd_state_idle(void)
        struct sched_domain *sd;
        int cpu = smp_processor_id();
 
-       if (test_bit(NOHZ_IDLE, nohz_flags(cpu)))
-               return;
-       set_bit(NOHZ_IDLE, nohz_flags(cpu));
-
        rcu_read_lock();
-       for_each_domain(cpu, sd)
+       sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd);
+
+       if (!sd || sd->nohz_idle)
+               goto unlock;
+       sd->nohz_idle = 1;
+
+       for (; sd; sd = sd->parent)
                atomic_dec(&sd->groups->sgp->nr_busy_cpus);
+unlock:
        rcu_read_unlock();
 }
 

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 605426a635885e9b5e796f85acc9a3a6cf897fec..4c225c4c7111d7baaa3dfa3d4ec0b3f9a966c593 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1303,7 +1303,6 @@ extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
 enum rq_nohz_flag_bits {
        NOHZ_TICK_STOPPED,
        NOHZ_BALANCE_KICK,
-       NOHZ_IDLE,
 };
 
 #define nohz_flags(cpu)        (&cpu_rq(cpu)->nohz_flags)