[GIT PULL] scheduler fixes

From: Ingo Molnar
Date: Tue Sep 12 2017 - 11:36:07 EST


Linus,

Please pull the latest sched-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

# HEAD: 46123355af729514e6fa8b8a9dd1e645e61a6466 sched/fair: Fix nuisance kernel-doc warning

Three fixes:

- fix a suspend/resume cpusets bug
- fix a !CONFIG_NUMA_BALANCING bug
- fix a kerneldoc warning

Thanks,

Ingo

------------------>
Peter Zijlstra (2):
sched/fair: Fix wake_affine_llc() balancing rules
sched/cpuset/pm: Fix cpuset vs. suspend-resume bugs

Randy Dunlap (1):
sched/fair: Fix nuisance kernel-doc warning


include/linux/cpuset.h | 6 ++++++
kernel/cgroup/cpuset.c | 16 +++++++++++++++-
kernel/power/process.c | 5 ++++-
kernel/sched/core.c | 7 +++----
kernel/sched/fair.c | 4 ++--
5 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index e74655d941b7..a1e6a33a4b03 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -51,7 +51,9 @@ static inline void cpuset_dec(void)

extern int cpuset_init(void);
extern void cpuset_init_smp(void);
+extern void cpuset_force_rebuild(void);
extern void cpuset_update_active_cpus(void);
+extern void cpuset_wait_for_hotplug(void);
extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
@@ -164,11 +166,15 @@ static inline bool cpusets_enabled(void) { return false; }
static inline int cpuset_init(void) { return 0; }
static inline void cpuset_init_smp(void) {}

+static inline void cpuset_force_rebuild(void) { }
+
static inline void cpuset_update_active_cpus(void)
{
partition_sched_domains(1, NULL, NULL);
}

+static inline void cpuset_wait_for_hotplug(void) { }
+
static inline void cpuset_cpus_allowed(struct task_struct *p,
struct cpumask *mask)
{
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 2f4039bafebb..0513ee39698b 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2267,6 +2267,13 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs)
mutex_unlock(&cpuset_mutex);
}

+static bool force_rebuild;
+
+void cpuset_force_rebuild(void)
+{
+ force_rebuild = true;
+}
+
/**
* cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset
*
@@ -2341,8 +2348,10 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
}

/* rebuild sched domains if cpus_allowed has changed */
- if (cpus_updated)
+ if (cpus_updated || force_rebuild) {
+ force_rebuild = false;
rebuild_sched_domains();
+ }
}

void cpuset_update_active_cpus(void)
@@ -2355,6 +2364,11 @@ void cpuset_update_active_cpus(void)
schedule_work(&cpuset_hotplug_work);
}

+void cpuset_wait_for_hotplug(void)
+{
+ flush_work(&cpuset_hotplug_work);
+}
+
/*
* Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY].
* Call this routine anytime after node_states[N_MEMORY] changes.
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 78672d324a6e..50f25cb370c6 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -20,8 +20,9 @@
#include <linux/workqueue.h>
#include <linux/kmod.h>
#include <trace/events/power.h>
+#include <linux/cpuset.h>

-/*
+/*
* Timeout for stopping processes
*/
unsigned int __read_mostly freeze_timeout_msecs = 20 * MSEC_PER_SEC;
@@ -202,6 +203,8 @@ void thaw_processes(void)
__usermodehelper_set_disable_depth(UMH_FREEZING);
thaw_workqueues();

+ cpuset_wait_for_hotplug();
+
read_lock(&tasklist_lock);
for_each_process_thread(g, p) {
/* No other threads should have PF_SUSPEND_TASK set */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6d2c7ff9ba98..136a76d80dbf 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5556,16 +5556,15 @@ static void cpuset_cpu_active(void)
* operation in the resume sequence, just build a single sched
* domain, ignoring cpusets.
*/
- num_cpus_frozen--;
- if (likely(num_cpus_frozen)) {
- partition_sched_domains(1, NULL, NULL);
+ partition_sched_domains(1, NULL, NULL);
+ if (--num_cpus_frozen)
return;
- }
/*
* This is the last CPU online operation. So fall through and
* restore the original sched domains by considering the
* cpuset configurations.
*/
+ cpuset_force_rebuild();
}
cpuset_update_active_cpus();
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8d5868771cb3..8415d1ec2b84 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5435,7 +5435,7 @@ wake_affine_llc(struct sched_domain *sd, struct task_struct *p,
return false;

/* if this cache has capacity, come here */
- if (this_stats.has_capacity && this_stats.nr_running < prev_stats.nr_running+1)
+ if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running)
return true;

/*
@@ -7719,7 +7719,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
* number.
*
* Return: 1 when packing is required and a task should be moved to
- * this CPU. The amount of the imbalance is returned in *imbalance.
+ * this CPU. The amount of the imbalance is returned in env->imbalance.
*
* @env: The load balancing environment.
* @sds: Statistics of the sched_domain which is to be packed