Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Add the SYSTEM_SCHEDULING bootup state to move various scheduler
     debug checks earlier into the bootup. This turns silent and
     sporadically deadly bugs into nice, deterministic splats. Fix some
     of the splats that triggered. (Thomas Gleixner)

   - A round of restructuring and refactoring of the load-balancing and
     topology code (Peter Zijlstra)

   - Another round of consolidating ~20 of incremental scheduler code
     history: this time in terms of wait-queue nomenclature. (I didn't
     get much feedback on these renaming patches, and we can still
     easily change any names I might have misplaced, so if anyone hates
     a new name, please holler and I'll fix it.) (Ingo Molnar)

   - sched/numa improvements, fixes and updates (Rik van Riel)

   - Another round of x86/tsc scheduler clock code improvements, in hope
     of making it more robust (Peter Zijlstra)

   - Improve NOHZ behavior (Frederic Weisbecker)

   - Deadline scheduler improvements and fixes (Luca Abeni, Daniel
     Bristot de Oliveira)

   - Simplify and optimize the topology setup code (Lauro Ramos
     Venancio)

   - Debloat and decouple scheduler code some more (Nicolas Pitre)

   - Simplify code by making better use of llist primitives (Byungchul
     Park)

   - ... plus other fixes and improvements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (103 commits)
  sched/cputime: Refactor the cputime_adjust() code
  sched/debug: Expose the number of RT/DL tasks that can migrate
  sched/numa: Hide numa_wake_affine() from UP build
  sched/fair: Remove effective_load()
  sched/numa: Implement NUMA node level wake_affine()
  sched/fair: Simplify wake_affine() for the single socket case
  sched/numa: Override part of migrate_degrades_locality() when idle balancing
  sched/rt: Move RT related code from sched/core.c to sched/rt.c
  sched/deadline: Move DL related code from sched/core.c to sched/deadline.c
  sched/cpuset: Only offer CONFIG_CPUSETS if SMP is enabled
  sched/fair: Spare idle load balancing on nohz_full CPUs
  nohz: Move idle balancer registration to the idle path
  sched/loadavg: Generalize "_idle" naming to "_nohz"
  sched/core: Drop the unused try_get_task_struct() helper function
  sched/fair: WARN() and refuse to set buddy when !se->on_rq
  sched/debug: Fix SCHED_WARN_ON() to return a value on !CONFIG_SCHED_DEBUG as well
  sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
  sched/wait: Move bit_wait_table[] and related functionality from sched/core.c to sched/wait_bit.c
  sched/wait: Split out the wait_bit*() APIs from <linux/wait.h> into <linux/wait_bit.h>
  sched/wait: Re-adjust macro line continuation backslashes in <linux/wait.h>
  ...

2 files changed, 23 insertions, 5 deletions

diff --git a/init/Kconfig b/init/Kconfig
index bc4c180..ee0f03b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -809,6 +809,7 @@ config CGROUP_HUGETLB
 
 config CPUSETS
 	bool "Cpuset controller"
+	depends on SMP
 	help
 	  This option will let you create and manage CPUSETs which
 	  allow dynamically partitioning a system into sets of CPUs and
diff --git a/init/main.c b/init/main.c
index f866510..df58a41 100644
--- a/init/main.c
+++ b/init/main.c
@@ -389,6 +389,7 @@ static __initdata DECLARE_COMPLETION(kthreadd_done);
 
 static noinline void __ref rest_init(void)
 {
+	struct task_struct *tsk;
 	int pid;
 
 	rcu_scheduler_starting();
@@ -397,12 +398,32 @@ static noinline void __ref rest_init(void)
 	 * the init task will end up wanting to create kthreads, which, if
 	 * we schedule it before we create kthreadd, will OOPS.
 	 */
-	kernel_thread(kernel_init, NULL, CLONE_FS);
+	pid = kernel_thread(kernel_init, NULL, CLONE_FS);
+	/*
+	 * Pin init on the boot CPU. Task migration is not properly working
+	 * until sched_init_smp() has been run. It will set the allowed
+	 * CPUs for init to the non isolated CPUs.
+	 */
+	rcu_read_lock();
+	tsk = find_task_by_pid_ns(pid, &init_pid_ns);
+	set_cpus_allowed_ptr(tsk, cpumask_of(smp_processor_id()));
+	rcu_read_unlock();
+
 	numa_default_policy();
 	pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
 	rcu_read_lock();
 	kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
 	rcu_read_unlock();
+
+	/*
+	 * Enable might_sleep() and smp_processor_id() checks.
+	 * They cannot be enabled earlier because with CONFIG_PRREMPT=y
+	 * kernel_thread() would trigger might_sleep() splats. With
+	 * CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled
+	 * already, but it's stuck on the kthreadd_done completion.
+	 */
+	system_state = SYSTEM_SCHEDULING;
+
 	complete(&kthreadd_done);
 
 	/*
@@ -1015,10 +1036,6 @@ static noinline void __init kernel_init_freeable(void)
 	 * init can allocate pages on any node
 	 */
 	set_mems_allowed(node_states[N_MEMORY]);
-	/*
-	 * init can run on any cpu.
-	 */
-	set_cpus_allowed_ptr(current, cpu_all_mask);
 
 	cad_pid = task_pid(current);