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 scheduler changes in this cycle were:

   - support Intel Turbo Boost Max Technology 3.0 (TBM3) by introducig a
     notion of 'better cores', which the scheduler will prefer to
     schedule single threaded workloads on. (Tim Chen, Srinivas
     Pandruvada)

   - enhance the handling of asymmetric capacity CPUs further (Morten
     Rasmussen)

   - improve/fix load handling when moving tasks between task groups
     (Vincent Guittot)

   - simplify and clean up the cputime code (Stanislaw Gruszka)

   - improve mass fork()ed task spread a.k.a. hackbench speedup (Vincent
     Guittot)

   - make struct kthread kmalloc()ed and related fixes (Oleg Nesterov)

   - add uaccess atomicity debugging (when using access_ok() in the
     wrong context), under CONFIG_DEBUG_ATOMIC_SLEEP=y (Peter Zijlstra)

   - implement various fixes, cleanups and other enhancements (Daniel
     Bristot de Oliveira, Martin Schwidefsky, Rafael J. Wysocki)"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  sched/core: Use load_avg for selecting idlest group
  sched/core: Fix find_idlest_group() for fork
  kthread: Don't abuse kthread_create_on_cpu() in __kthread_create_worker()
  kthread: Don't use to_live_kthread() in kthread_[un]park()
  kthread: Don't use to_live_kthread() in kthread_stop()
  Revert "kthread: Pin the stack via try_get_task_stack()/put_task_stack() in to_live_kthread() function"
  kthread: Make struct kthread kmalloc'ed
  x86/uaccess, sched/preempt: Verify access_ok() context
  sched/x86: Make CONFIG_SCHED_MC_PRIO=y easier to enable
  sched/x86: Change CONFIG_SCHED_ITMT to CONFIG_SCHED_MC_PRIO
  x86/sched: Use #include <linux/mutex.h> instead of #include <asm/mutex.h>
  cpufreq/intel_pstate: Use CPPC to get max performance
  acpi/bus: Set _OSC for diverse core support
  acpi/bus: Enable HWP CPPC objects
  x86/sched: Add SD_ASYM_PACKING flags to x86 ITMT CPU
  x86/sysctl: Add sysctl for ITMT scheduling feature
  x86: Enable Intel Turbo Boost Max Technology 3.0
  x86/topology: Define x86's arch_update_cpu_topology
  sched: Extend scheduler's asym packing
  sched/fair: Clean up the tunable parameter definitions
  ...

arch/x86/Kconfig

@@ -939,6 +939,27 @@ config SCHED_MC
 	  making when dealing with multi-core CPU chips at a cost of slightly
 	  increased overhead in some places. If unsure say N here.
 
+config SCHED_MC_PRIO
+	bool "CPU core priorities scheduler support"
+	depends on SCHED_MC && CPU_SUP_INTEL
+	select X86_INTEL_PSTATE
+	select CPU_FREQ
+	default y
+	---help---
+	  Intel Turbo Boost Max Technology 3.0 enabled CPUs have a
+	  core ordering determined at manufacturing time, which allows
+	  certain cores to reach higher turbo frequencies (when running
+	  single threaded workloads) than others.
+
+	  Enabling this kernel feature teaches the scheduler about
+	  the TBM3 (aka ITMT) priority order of the CPU cores and adjusts the
+	  scheduler's CPU selection logic accordingly, so that higher
+	  overall system performance can be achieved.
+
+	  This feature will have no effect on CPUs without this feature.
+
+	  If unsure say Y here.
+
 source "kernel/Kconfig.preempt"
 
 config UP_LATE_INIT

arch/x86/include/asm/preempt.h

@@ -24,7 +24,13 @@ static __always_inline int preempt_count(void)
 
 static __always_inline void preempt_count_set(int pc)
 {
-	raw_cpu_write_4(__preempt_count, pc);
+	int old, new;
+
+	do {
+		old = raw_cpu_read_4(__preempt_count);
+		new = (old & PREEMPT_NEED_RESCHED) |
+			(pc & ~PREEMPT_NEED_RESCHED);
+	} while (raw_cpu_cmpxchg_4(__preempt_count, old, new) != old);
 }
 
 /*

arch/x86/include/asm/topology.h

@@ -146,4 +146,36 @@ struct pci_bus;
 int x86_pci_root_bus_node(int bus);
 void x86_pci_root_bus_resources(int bus, struct list_head *resources);
 
+extern bool x86_topology_update;
+
+#ifdef CONFIG_SCHED_MC_PRIO
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(int, sched_core_priority);
+extern unsigned int __read_mostly sysctl_sched_itmt_enabled;
+
+/* Interface to set priority of a cpu */
+void sched_set_itmt_core_prio(int prio, int core_cpu);
+
+/* Interface to notify scheduler that system supports ITMT */
+int sched_set_itmt_support(void);
+
+/* Interface to notify scheduler that system revokes ITMT support */
+void sched_clear_itmt_support(void);
+
+#else /* CONFIG_SCHED_MC_PRIO */
+
+#define sysctl_sched_itmt_enabled	0
+static inline void sched_set_itmt_core_prio(int prio, int core_cpu)
+{
+}
+static inline int sched_set_itmt_support(void)
+{
+	return 0;
+}
+static inline void sched_clear_itmt_support(void)
+{
+}
+#endif /* CONFIG_SCHED_MC_PRIO */
+
 #endif /* _ASM_X86_TOPOLOGY_H */

arch/x86/include/asm/uaccess.h

@@ -68,6 +68,12 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
 	__chk_range_not_ok((unsigned long __force)(addr), size, limit); \
 })
 
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+# define WARN_ON_IN_IRQ()	WARN_ON_ONCE(!in_task())
+#else
+# define WARN_ON_IN_IRQ()
+#endif
+
 /**
  * access_ok: - Checks if a user space pointer is valid
  * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE.  Note that
@@ -88,8 +94,11 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
  * checks that the pointer is in the user space range - after calling
  * this function, memory access functions may still return -EFAULT.
  */
-#define access_ok(type, addr, size) \
-	likely(!__range_not_ok(addr, size, user_addr_max()))
+#define access_ok(type, addr, size)					\
+({									\
+	WARN_ON_IN_IRQ();						\
+	likely(!__range_not_ok(addr, size, user_addr_max()));		\
+})
 
 /*
  * These are the main single-value transfer routines.  They automatically

arch/x86/kernel/Makefile

@@ -123,6 +123,7 @@ obj-$(CONFIG_EFI)			+= sysfb_efi.o
 
 obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 obj-$(CONFIG_TRACING)			+= tracepoint.o
+obj-$(CONFIG_SCHED_MC_PRIO)		+= itmt.o
 
 ifdef CONFIG_FRAME_POINTER
 obj-y					+= unwind_frame.o

arch/x86/kernel/apm_32.c

@@ -906,14 +906,14 @@ static int apm_cpu_idle(struct cpuidle_device *dev,
 	static int use_apm_idle; /* = 0 */
 	static unsigned int last_jiffies; /* = 0 */
 	static unsigned int last_stime; /* = 0 */
-	cputime_t stime;
+	cputime_t stime, utime;
 
 	int apm_idle_done = 0;
 	unsigned int jiffies_since_last_check = jiffies - last_jiffies;
 	unsigned int bucket;
 
 recalc:
-	task_cputime(current, NULL, &stime);
+	task_cputime(current, &utime, &stime);
 	if (jiffies_since_last_check > IDLE_CALC_LIMIT) {
 		use_apm_idle = 0;
 	} else if (jiffies_since_last_check > idle_period) {

arch/x86/kernel/itmt.c

@@ -0,0 +1,215 @@
+/*
+ * itmt.c: Support Intel Turbo Boost Max Technology 3.0
+ *
+ * (C) Copyright 2016 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * On platforms supporting Intel Turbo Boost Max Technology 3.0, (ITMT),
+ * the maximum turbo frequencies of some cores in a CPU package may be
+ * higher than for the other cores in the same package.  In that case,
+ * better performance can be achieved by making the scheduler prefer
+ * to run tasks on the CPUs with higher max turbo frequencies.
+ *
+ * This file provides functions and data structures for enabling the
+ * scheduler to favor scheduling on cores can be boosted to a higher
+ * frequency under ITMT.
+ */
+
+#include <linux/sched.h>
+#include <linux/cpumask.h>
+#include <linux/cpuset.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/sysctl.h>
+#include <linux/nodemask.h>
+
+static DEFINE_MUTEX(itmt_update_mutex);
+DEFINE_PER_CPU_READ_MOSTLY(int, sched_core_priority);
+
+/* Boolean to track if system has ITMT capabilities */
+static bool __read_mostly sched_itmt_capable;
+
+/*
+ * Boolean to control whether we want to move processes to cpu capable
+ * of higher turbo frequency for cpus supporting Intel Turbo Boost Max
+ * Technology 3.0.
+ *
+ * It can be set via /proc/sys/kernel/sched_itmt_enabled
+ */
+unsigned int __read_mostly sysctl_sched_itmt_enabled;
+
+static int sched_itmt_update_handler(struct ctl_table *table, int write,
+				     void __user *buffer, size_t *lenp,
+				     loff_t *ppos)
+{
+	unsigned int old_sysctl;
+	int ret;
+
+	mutex_lock(&itmt_update_mutex);
+
+	if (!sched_itmt_capable) {
+		mutex_unlock(&itmt_update_mutex);
+		return -EINVAL;
+	}
+
+	old_sysctl = sysctl_sched_itmt_enabled;
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+	if (!ret && write && old_sysctl != sysctl_sched_itmt_enabled) {
+		x86_topology_update = true;
+		rebuild_sched_domains();
+	}
+
+	mutex_unlock(&itmt_update_mutex);
+
+	return ret;
+}
+
+static unsigned int zero;
+static unsigned int one = 1;
+static struct ctl_table itmt_kern_table[] = {
+	{
+		.procname	= "sched_itmt_enabled",
+		.data		= &sysctl_sched_itmt_enabled,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sched_itmt_update_handler,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{}
+};
+
+static struct ctl_table itmt_root_table[] = {
+	{
+		.procname	= "kernel",
+		.mode		= 0555,
+		.child		= itmt_kern_table,
+	},
+	{}
+};
+
+static struct ctl_table_header *itmt_sysctl_header;
+
+/**
+ * sched_set_itmt_support() - Indicate platform supports ITMT
+ *
+ * This function is used by the OS to indicate to scheduler that the platform
+ * is capable of supporting the ITMT feature.
+ *
+ * The current scheme has the pstate driver detects if the system
+ * is ITMT capable and call sched_set_itmt_support.
+ *
+ * This must be done only after sched_set_itmt_core_prio
+ * has been called to set the cpus' priorities.
+ * It must not be called with cpu hot plug lock
+ * held as we need to acquire the lock to rebuild sched domains
+ * later.
+ *
+ * Return: 0 on success
+ */
+int sched_set_itmt_support(void)
+{
+	mutex_lock(&itmt_update_mutex);
+
+	if (sched_itmt_capable) {
+		mutex_unlock(&itmt_update_mutex);
+		return 0;
+	}
+
+	itmt_sysctl_header = register_sysctl_table(itmt_root_table);
+	if (!itmt_sysctl_header) {
+		mutex_unlock(&itmt_update_mutex);
+		return -ENOMEM;
+	}
+
+	sched_itmt_capable = true;
+
+	sysctl_sched_itmt_enabled = 1;
+
+	if (sysctl_sched_itmt_enabled) {
+		x86_topology_update = true;
+		rebuild_sched_domains();
+	}
+
+	mutex_unlock(&itmt_update_mutex);
+
+	return 0;
+}
+
+/**
+ * sched_clear_itmt_support() - Revoke platform's support of ITMT
+ *
+ * This function is used by the OS to indicate that it has
+ * revoked the platform's support of ITMT feature.
+ *
+ * It must not be called with cpu hot plug lock
+ * held as we need to acquire the lock to rebuild sched domains
+ * later.
+ */
+void sched_clear_itmt_support(void)
+{
+	mutex_lock(&itmt_update_mutex);
+
+	if (!sched_itmt_capable) {
+		mutex_unlock(&itmt_update_mutex);
+		return;
+	}
+	sched_itmt_capable = false;
+
+	if (itmt_sysctl_header) {
+		unregister_sysctl_table(itmt_sysctl_header);
+		itmt_sysctl_header = NULL;
+	}
+
+	if (sysctl_sched_itmt_enabled) {
+		/* disable sched_itmt if we are no longer ITMT capable */
+		sysctl_sched_itmt_enabled = 0;
+		x86_topology_update = true;
+		rebuild_sched_domains();
+	}
+
+	mutex_unlock(&itmt_update_mutex);
+}
+
+int arch_asym_cpu_priority(int cpu)
+{
+	return per_cpu(sched_core_priority, cpu);
+}
+
+/**
+ * sched_set_itmt_core_prio() - Set CPU priority based on ITMT
+ * @prio:	Priority of cpu core
+ * @core_cpu:	The cpu number associated with the core
+ *
+ * The pstate driver will find out the max boost frequency
+ * and call this function to set a priority proportional
+ * to the max boost frequency. CPU with higher boost
+ * frequency will receive higher priority.
+ *
+ * No need to rebuild sched domain after updating
+ * the CPU priorities. The sched domains have no
+ * dependency on CPU priorities.
+ */
+void sched_set_itmt_core_prio(int prio, int core_cpu)
+{
+	int cpu, i = 1;
+
+	for_each_cpu(cpu, topology_sibling_cpumask(core_cpu)) {
+		int smt_prio;
+
+		/*
+		 * Ensure that the siblings are moved to the end
+		 * of the priority chain and only used when
+		 * all other high priority cpus are out of capacity.
+		 */
+		smt_prio = prio * smp_num_siblings / i;
+		per_cpu(sched_core_priority, cpu) = smt_prio;
+		i++;
+	}
+}

arch/x86/kernel/smpboot.c

@@ -109,6 +109,17 @@ static bool logical_packages_frozen __read_mostly;
 /* Maximum number of SMT threads on any online core */
 int __max_smt_threads __read_mostly;
 
+/* Flag to indicate if a complete sched domain rebuild is required */
+bool x86_topology_update;
+
+int arch_update_cpu_topology(void)
+{
+	int retval = x86_topology_update;
+
+	x86_topology_update = false;
+	return retval;
+}
+
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 {
 	unsigned long flags;
@@ -471,22 +482,42 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 	return false;
 }
 
+#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)
+static inline int x86_sched_itmt_flags(void)
+{
+	return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0;
+}
+
+#ifdef CONFIG_SCHED_MC
+static int x86_core_flags(void)
+{
+	return cpu_core_flags() | x86_sched_itmt_flags();
+}
+#endif
+#ifdef CONFIG_SCHED_SMT
+static int x86_smt_flags(void)
+{
+	return cpu_smt_flags() | x86_sched_itmt_flags();
+}
+#endif
+#endif
+
 static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
 #ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
 #endif
 #ifdef CONFIG_SCHED_MC
-	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
 #endif
 	{ NULL, },
 };
 
 static struct sched_domain_topology_level x86_topology[] = {
 #ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
 #endif
 #ifdef CONFIG_SCHED_MC
-	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
 #endif
 	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
 	{ NULL, },