summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/itmt.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/itmt.c')
-rw-r--r--arch/x86/kernel/itmt.c183
1 files changed, 183 insertions, 0 deletions
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
new file mode 100644
index 0000000000..ee4fe8cdb8
--- /dev/null
+++ b/arch/x86/kernel/itmt.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * itmt.c: Support Intel Turbo Boost Max Technology 3.0
+ *
+ * (C) Copyright 2016 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * 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/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 *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 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 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+ {}
+};
+
+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("kernel", itmt_kern_table);
+ if (!itmt_sysctl_header) {
+ mutex_unlock(&itmt_update_mutex);
+ return -ENOMEM;
+ }
+
+ sched_itmt_capable = true;
+
+ sysctl_sched_itmt_enabled = 1;
+
+ 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
+ * @cpu: The CPU number
+ *
+ * The pstate driver will find out the max boost frequency
+ * and call this function to set a priority proportional
+ * to the max boost frequency. CPUs 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 cpu)
+{
+ per_cpu(sched_core_priority, cpu) = prio;
+}