15 files changed, 341 insertions, 32 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 44a44b49eb3a..835d55d52104 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -513,6 +513,9 @@ config HAVE_CONTEXT_TRACKING
 config HAVE_VIRT_CPU_ACCOUNTING
 	bool
 
+config ARCH_HAS_SCALED_CPUTIME
+	bool
+
 config HAVE_VIRT_CPU_ACCOUNTING_GEN
 	bool
 	default y if 64BIT
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 6f892b94e906..021f44ab4bfb 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -68,7 +68,7 @@ void vtime_account_user(struct task_struct *tsk)
 
 	if (ti->ac_utime) {
 		delta_utime = cycle_to_cputime(ti->ac_utime);
-		account_user_time(tsk, delta_utime, delta_utime);
+		account_user_time(tsk, delta_utime);
 		ti->ac_utime = 0;
 	}
 }
@@ -112,7 +112,7 @@ void vtime_account_system(struct task_struct *tsk)
 {
 	cputime_t delta = vtime_delta(tsk);
 
-	account_system_time(tsk, 0, delta, delta);
+	account_system_time(tsk, 0, delta);
 }
 EXPORT_SYMBOL_GPL(vtime_account_system);
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 65fba4c34cd7..c7f120aaa98f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -160,6 +160,7 @@ config PPC
 	select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select GENERIC_CPU_AUTOPROBE
 	select HAVE_VIRT_CPU_ACCOUNTING
+	select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
 	select HAVE_ARCH_HARDENED_USERCOPY
 	select HAVE_KERNEL_GZIP
 
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 4f60db074725..aa2e6a34b872 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -46,26 +46,12 @@ extern cputime_t cputime_one_jiffy;
  * Convert cputime <-> jiffies
  */
 extern u64 __cputime_jiffies_factor;
-DECLARE_PER_CPU(unsigned long, cputime_last_delta);
-DECLARE_PER_CPU(unsigned long, cputime_scaled_last_delta);
 
 static inline unsigned long cputime_to_jiffies(const cputime_t ct)
 {
 	return mulhdu((__force u64) ct, __cputime_jiffies_factor);
 }
 
-/* Estimate the scaled cputime by scaling the real cputime based on
- * the last scaled to real ratio */
-static inline cputime_t cputime_to_scaled(const cputime_t ct)
-{
-	if (cpu_has_feature(CPU_FTR_SPURR) &&
-	    __this_cpu_read(cputime_last_delta))
-		return (__force u64) ct *
-			__this_cpu_read(cputime_scaled_last_delta) /
-			__this_cpu_read(cputime_last_delta);
-	return ct;
-}
-
 static inline cputime_t jiffies_to_cputime(const unsigned long jif)
 {
 	u64 ct;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index bc3f7d0d7b79..be9751f1cb2a 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -164,8 +164,6 @@ u64 __cputime_sec_factor;
 EXPORT_SYMBOL(__cputime_sec_factor);
 u64 __cputime_clockt_factor;
 EXPORT_SYMBOL(__cputime_clockt_factor);
-DEFINE_PER_CPU(unsigned long, cputime_last_delta);
-DEFINE_PER_CPU(unsigned long, cputime_scaled_last_delta);
 
 cputime_t cputime_one_jiffy;
 
@@ -360,7 +358,8 @@ void vtime_account_system(struct task_struct *tsk)
 	unsigned long delta, sys_scaled, stolen;
 
 	delta = vtime_delta(tsk, &sys_scaled, &stolen);
-	account_system_time(tsk, 0, delta, sys_scaled);
+	account_system_time(tsk, 0, delta);
+	tsk->stimescaled += sys_scaled;
 	if (stolen)
 		account_steal_time(stolen);
 }
@@ -393,7 +392,8 @@ void vtime_account_user(struct task_struct *tsk)
 	acct->user_time = 0;
 	acct->user_time_scaled = 0;
 	acct->utime_sspurr = 0;
-	account_user_time(tsk, utime, utimescaled);
+	account_user_time(tsk, utime);
+	tsk->utimescaled += utimescaled;
 }
 
 #ifdef CONFIG_PPC32
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 426481d4cc86..028f97be5bae 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -171,6 +171,7 @@ config S390
 	select SYSCTL_EXCEPTION_TRACE
 	select TTY
 	select VIRT_CPU_ACCOUNTING
+	select ARCH_HAS_SCALED_CPUTIME
 	select VIRT_TO_BUS
 	select HAVE_NMI
 
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 856e30d8463f..1bd5dde2d5a9 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -137,8 +137,10 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
 		user_scaled = (user_scaled * mult) / div;
 		system_scaled = (system_scaled * mult) / div;
 	}
-	account_user_time(tsk, user, user_scaled);
-	account_system_time(tsk, hardirq_offset, system, system_scaled);
+	account_user_time(tsk, user);
+	tsk->utimescaled += user_scaled;
+	account_system_time(tsk, hardirq_offset, system);
+	tsk->stimescaled += system_scaled;
 
 	steal = S390_lowcore.steal_timer;
 	if ((s64) steal > 0) {
@@ -202,7 +204,8 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 
 		system_scaled = (system_scaled * mult) / div;
 	}
-	account_system_time(tsk, 0, system, system_scaled);
+	account_system_time(tsk, 0, system);
+	tsk->stimescaled += system_scaled;
 
 	virt_timer_forward(system);
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index bada636d1065..b50e5eeefd21 100644
--- a/arch/x86/Kconfig
+++ b/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
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 17f218645701..ec1f3c651150 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/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);
 }
 
 /*
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index cf75871d2f81..6358a85e2270 100644
--- a/arch/x86/include/asm/topology.h
+++ b/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 */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index faf3687f1035..ea148313570f 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/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
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 79076d75bdbf..05110c1097ae 100644
--- a/arch/x86/kernel/Makefile
+++ b/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
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 51287cd90bf6..643818a7688b 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/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) {
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
new file mode 100644
index 000000000000..cb9c1ed1d391
--- /dev/null
+++ b/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++;
+	}
+}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index b9f02383f372..118e792a7be6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/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, },