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

…inux/kernel/git/tip/tip

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

   - Make nohz housekeeping processing more permissive and less
     intrusive to isolated CPUs

   - Decouple CPU-bound workqueue acconting from the scheduler and move
     it into the workqueue code.

   - Optimize topology building

   - Better handle quota and period overflows

   - Add more RCU annotations

   - Comment updates, misc cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
  nohz_full: Allow the boot CPU to be nohz_full
  sched/isolation: Require a present CPU in housekeeping mask
  kernel/cpu: Allow non-zero CPU to be primary for suspend / kexec freeze
  power/suspend: Add function to disable secondaries for suspend
  sched/core: Allow the remote scheduler tick to be started on CPU0
  sched/nohz: Run NOHZ idle load balancer on HK_FLAG_MISC CPUs
  sched/debug: Fix spelling mistake "logaritmic" -> "logarithmic"
  sched/topology: Update init_sched_domains() comment
  cgroup/cpuset: Update stale generate_sched_domains() comments
  sched/core: Check quota and period overflow at usec to nsec conversion
  sched/core: Handle overflow in cpu_shares_write_u64
  sched/rt: Check integer overflow at usec to nsec conversion
  sched/core: Fix typo in comment
  sched/core: Make some functions static
  sched/core: Unify p->on_rq updates
  sched/core: Remove ttwu_activate()
  sched/core, workqueues: Distangle worker accounting from rq lock
  sched/fair: Remove unneeded prototype of capacity_of()
  sched/topology: Skip duplicate group rewrites in build_sched_groups()
  sched/topology: Fix build_sched_groups() comment
  ...

arch/powerpc/Kconfig

@@ -313,6 +313,10 @@ config ARCH_SUSPEND_POSSIBLE
 		   (PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \
 		   || 44x || 40x
 
+config ARCH_SUSPEND_NONZERO_CPU
+	def_bool y
+	depends on PPC_POWERNV || PPC_PSERIES
+
 config PPC_DCR_NATIVE
 	bool
 

include/linux/cpu.h

@@ -137,9 +137,26 @@ static inline int disable_nonboot_cpus(void)
 	return freeze_secondary_cpus(0);
 }
 extern void enable_nonboot_cpus(void);
+
+static inline int suspend_disable_secondary_cpus(void)
+{
+	int cpu = 0;
+
+	if (IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU))
+		cpu = -1;
+
+	return freeze_secondary_cpus(cpu);
+}
+static inline void suspend_enable_secondary_cpus(void)
+{
+	return enable_nonboot_cpus();
+}
+
 #else /* !CONFIG_PM_SLEEP_SMP */
 static inline int disable_nonboot_cpus(void) { return 0; }
 static inline void enable_nonboot_cpus(void) {}
+static inline int suspend_disable_secondary_cpus(void) { return 0; }
+static inline void suspend_enable_secondary_cpus(void) { }
 #endif /* !CONFIG_PM_SLEEP_SMP */
 
 void cpu_startup_entry(enum cpuhp_state state);

include/linux/rcuwait.h

@@ -18,7 +18,7 @@
  * awoken.
  */
 struct rcuwait {
-	struct task_struct *task;
+	struct task_struct __rcu *task;
 };
 
 #define __RCUWAIT_INITIALIZER(name)		\

include/linux/sched/topology.h

@@ -76,8 +76,8 @@ struct sched_domain_shared {
 
 struct sched_domain {
 	/* These fields must be setup */
-	struct sched_domain *parent;	/* top domain must be null terminated */
-	struct sched_domain *child;	/* bottom domain must be null terminated */
+	struct sched_domain __rcu *parent;	/* top domain must be null terminated */
+	struct sched_domain __rcu *child;	/* bottom domain must be null terminated */
 	struct sched_group *groups;	/* the balancing groups of the domain */
 	unsigned long min_interval;	/* Minimum balance interval ms */
 	unsigned long max_interval;	/* Maximum balance interval ms */

kernel/cgroup/cpuset.c

@@ -740,11 +740,10 @@ static inline int nr_cpusets(void)
  * Must be called with cpuset_mutex held.
  *
  * The three key local variables below are:
- *    q  - a linked-list queue of cpuset pointers, used to implement a
- *	   top-down scan of all cpusets.  This scan loads a pointer
- *	   to each cpuset marked is_sched_load_balance into the
- *	   array 'csa'.  For our purposes, rebuilding the schedulers
- *	   sched domains, we can ignore !is_sched_load_balance cpusets.
+ *    cp - cpuset pointer, used (together with pos_css) to perform a
+ *	   top-down scan of all cpusets. For our purposes, rebuilding
+ *	   the schedulers sched domains, we can ignore !is_sched_load_
+ *	   balance cpusets.
  *  csa  - (for CpuSet Array) Array of pointers to all the cpusets
  *	   that need to be load balanced, for convenient iterative
  *	   access by the subsequent code that finds the best partition,
@@ -775,7 +774,7 @@ static inline int nr_cpusets(void)
 static int generate_sched_domains(cpumask_var_t **domains,
 			struct sched_domain_attr **attributes)
 {
-	struct cpuset *cp;	/* scans q */
+	struct cpuset *cp;	/* top-down scan of cpusets */
 	struct cpuset **csa;	/* array of all cpuset ptrs */
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */

kernel/cpu.c

@@ -9,6 +9,7 @@
 #include <linux/notifier.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/isolation.h>
 #include <linux/sched/task.h>
 #include <linux/sched/smt.h>
 #include <linux/unistd.h>
@@ -1199,8 +1200,15 @@ int freeze_secondary_cpus(int primary)
 	int cpu, error = 0;
 
 	cpu_maps_update_begin();
-	if (!cpu_online(primary))
+	if (primary == -1) {
 		primary = cpumask_first(cpu_online_mask);
+		if (!housekeeping_cpu(primary, HK_FLAG_TIMER))
+			primary = housekeeping_any_cpu(HK_FLAG_TIMER);
+	} else {
+		if (!cpu_online(primary))
+			primary = cpumask_first(cpu_online_mask);
+	}
+
 	/*
 	 * We take down all of the non-boot CPUs in one shot to avoid races
 	 * with the userspace trying to use the CPU hotplug at the same time

kernel/kexec_core.c

@@ -1150,7 +1150,7 @@ int kernel_kexec(void)
 		error = dpm_suspend_end(PMSG_FREEZE);
 		if (error)
 			goto Resume_devices;
-		error = disable_nonboot_cpus();
+		error = suspend_disable_secondary_cpus();
 		if (error)
 			goto Enable_cpus;
 		local_irq_disable();
@@ -1183,7 +1183,7 @@ int kernel_kexec(void)
  Enable_irqs:
 		local_irq_enable();
  Enable_cpus:
-		enable_nonboot_cpus();
+		suspend_enable_secondary_cpus();
 		dpm_resume_start(PMSG_RESTORE);
  Resume_devices:
 		dpm_resume_end(PMSG_RESTORE);

kernel/power/Kconfig

@@ -114,6 +114,15 @@ config PM_SLEEP_SMP
 	depends on PM_SLEEP
 	select HOTPLUG_CPU
 
+config PM_SLEEP_SMP_NONZERO_CPU
+	def_bool y
+	depends on PM_SLEEP_SMP
+	depends on ARCH_SUSPEND_NONZERO_CPU
+	---help---
+	If an arch can suspend (for suspend, hibernate, kexec, etc) on a
+	non-zero numbered CPU, it may define ARCH_SUSPEND_NONZERO_CPU. This
+	will allow nohz_full mask to include CPU0.
+
 config PM_AUTOSLEEP
 	bool "Opportunistic sleep"
 	depends on PM_SLEEP

kernel/power/hibernate.c

@@ -281,7 +281,7 @@ static int create_image(int platform_mode)
 	if (error || hibernation_test(TEST_PLATFORM))
 		goto Platform_finish;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error || hibernation_test(TEST_CPUS))
 		goto Enable_cpus;
 
@@ -323,7 +323,7 @@ static int create_image(int platform_mode)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_finish:
 	platform_finish(platform_mode);
@@ -417,7 +417,7 @@ int hibernation_snapshot(int platform_mode)
 
 int __weak hibernate_resume_nonboot_cpu_disable(void)
 {
-	return disable_nonboot_cpus();
+	return suspend_disable_secondary_cpus();
 }
 
 /**
@@ -486,7 +486,7 @@ static int resume_target_kernel(bool platform_mode)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Cleanup:
 	platform_restore_cleanup(platform_mode);
@@ -564,7 +564,7 @@ int hibernation_platform_enter(void)
 	if (error)
 		goto Platform_finish;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error)
 		goto Enable_cpus;
 
@@ -586,7 +586,7 @@ int hibernation_platform_enter(void)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_finish:
 	hibernation_ops->finish();

kernel/power/suspend.c

@@ -428,7 +428,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	if (suspend_test(TEST_PLATFORM))
 		goto Platform_wake;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error || suspend_test(TEST_CPUS))
 		goto Enable_cpus;
 
@@ -458,7 +458,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	BUG_ON(irqs_disabled());
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_wake:
 	platform_resume_noirq(state);