From a731ebe6f17bff9e7ca12ef227f9da4d5bdf8425 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 6 Sep 2017 12:51:31 +0200 Subject: [PATCH 1/3] sched/fair: Fix wake_affine_llc() balancing rules Chris Wilson reported that the SMT balance rules got the +1 on the wrong side, resulting in a bias towards the current LLC; which the load-balancer would then try and undo. Reported-by: Chris Wilson Tested-by: Chris Wilson Signed-off-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Fixes: 90001d67be2f ("sched/fair: Fix wake_affine() for !NUMA_BALANCING") Link: http://lkml.kernel.org/r/20170906105131.gqjmaextmn3u6tj2@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8d5868771cb3..9dd2ce1e5ca2 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; /* From 50e76632339d4655859523a39249dd95ee5e93e7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Sep 2017 11:13:38 +0200 Subject: [PATCH 2/3] sched/cpuset/pm: Fix cpuset vs. suspend-resume bugs Cpusets vs. suspend-resume is _completely_ broken. And it got noticed because it now resulted in non-cpuset usage breaking too. On suspend cpuset_cpu_inactive() doesn't call into cpuset_update_active_cpus() because it doesn't want to move tasks about, there is no need, all tasks are frozen and won't run again until after we've resumed everything. But this means that when we finally do call into cpuset_update_active_cpus() after resuming the last frozen cpu in cpuset_cpu_active(), the top_cpuset will not have any difference with the cpu_active_mask and this it will not in fact do _anything_. So the cpuset configuration will not be restored. This was largely hidden because we would unconditionally create identity domains and mobile users would not in fact use cpusets much. And servers what do use cpusets tend to not suspend-resume much. An addition problem is that we'd not in fact wait for the cpuset work to finish before resuming the tasks, allowing spurious migrations outside of the specified domains. Fix the rebuild by introducing cpuset_force_rebuild() and fix the ordering with cpuset_wait_for_hotplug(). Reported-by: Andy Lutomirski Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Tejun Heo Cc: Thomas Gleixner Fixes: deb7aa308ea2 ("cpuset: reorganize CPU / memory hotplug handling") Link: http://lkml.kernel.org/r/20170907091338.orwxrqkbfkki3c24@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/cpuset.h | 6 ++++++ kernel/cgroup/cpuset.c | 16 +++++++++++++++- kernel/power/process.c | 5 ++++- kernel/sched/core.c | 7 +++---- 4 files changed, 28 insertions(+), 6 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 @@ retry: 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 #include #include +#include -/* +/* * 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(); } From 46123355af729514e6fa8b8a9dd1e645e61a6466 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 10 Sep 2017 09:55:05 -0700 Subject: [PATCH 3/3] sched/fair: Fix nuisance kernel-doc warning Work around kernel-doc warning ('*' in Sphinx doc means "emphasis"): ../kernel/sched/fair.c:7584: WARNING: Inline emphasis start-string without end-string. Signed-off-by: Randy Dunlap Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/f18b30f9-6251-6d86-9d44-16501e386891@infradead.org Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9dd2ce1e5ca2..8415d1ec2b84 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7719,7 +7719,7 @@ next_group: * 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