[PATCH v6 4/9] x86: Enable Intel Turbo Boost Max Technology 3.0

[Tim Chen]

On platforms supporting Intel Turbo Boost Max Technology 3.0, 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
(and possibly lower energy consumption as well) can be achieved by
making the scheduler prefer to run tasks on the CPUs with higher max
turbo frequencies.

To that end, set up a core priority metric to abstract the core
preferences based on the maximum turbo frequency.  In that metric,
the cores with higher maximum turbo frequencies are higher-priority
than the other cores in the same package and that causes the scheduler
to favor them when making load-balancing decisions using the asymmertic
packing approach.  At the same time, the priority of SMT threads with a
higher CPU number is reduced so as to avoid scheduling tasks on all of
the threads that belong to a favored core before all of the other cores
have been given a task to run.

The priority metric will be initialized by the P-state driver with the
help of the sched_set_itmt_core_prio() function.  The P-state driver
will also determine whether or not ITMT is supported by the platform
and will call sched_set_itmt_support() to indicate that.

Signed-off-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@xxxxxxxxxxxxxxx>
---
 arch/x86/Kconfig                |   9 ++++
 arch/x86/include/asm/topology.h |  28 +++++++++++
 arch/x86/kernel/Makefile        |   1 +
 arch/x86/kernel/itmt.c          | 109 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 147 insertions(+)
 create mode 100644 arch/x86/kernel/itmt.c

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index bada636..25950f0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -939,6 +939,15 @@ 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_ITMT
+	bool "Intel Turbo Boost Max Technology (ITMT) scheduler support"
+	depends on SCHED_MC && CPU_SUP_INTEL && X86_INTEL_PSTATE
+	---help---
+	  ITMT enabled scheduler support improves the CPU scheduler's decision
+	  to move tasks to cpu core that can be boosted to a higher frequency
+	  than others. It will have better performance at a cost of slightly
+	  increased overhead in task migrations. If unsure say N here.
+
 source "kernel/Kconfig.preempt"
 
 config UP_LATE_INIT
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 323f61f..a73fb80 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -150,4 +150,32 @@ 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_ITMT
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(int, sched_core_priority);
+
+/* 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 */
+void sched_set_itmt_support(void);
+
+/* Interface to notify scheduler that system revokes ITMT support */
+void sched_clear_itmt_support(void);
+
+#else /* CONFIG_SCHED_ITMT */
+
+static inline void sched_set_itmt_core_prio(int prio, int core_cpu)
+{
+}
+static inline void sched_set_itmt_support(void)
+{
+}
+static inline void sched_clear_itmt_support(void)
+{
+}
+#endif /* CONFIG_SCHED_ITMT */
+
 #endif /* _ASM_X86_TOPOLOGY_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 79076d7..bbd0ebc 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_ITMT)		+= itmt.o
 
 ifdef CONFIG_FRAME_POINTER
 obj-y					+= unwind_frame.o
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
new file mode 100644
index 0000000..63c9b3e
--- /dev/null
+++ b/arch/x86/kernel/itmt.c
@@ -0,0 +1,109 @@
+/*
+ * itmt.c: Support Intel Turbo Boost Max Technology 3.0
+ *
+ * (C) Copyright 2016 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
+ *
+ * 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 <asm/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;
+
+/**
+ * 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.
+ */
+void sched_set_itmt_support(void)
+{
+	mutex_lock(&itmt_update_mutex);
+
+	sched_itmt_capable = true;
+
+	mutex_unlock(&itmt_update_mutex);
+}
+
+/**
+ * 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.
+ *
+ */
+void sched_clear_itmt_support(void)
+{
+	mutex_lock(&itmt_update_mutex);
+
+	sched_itmt_capable = false;
+
+	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++;
+	}
+}
-- 
2.5.5